handoff

# Handoff

Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save to the temporary directory of the user's OS — not the current workspace.

Include a "suggested skills" section in the document, which suggests skills that the agent should invoke.

Do not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.

Redact any sensitive information, such as API keys, passwords, or personally identifiable information.

If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.

## Invocation Triggers

**Explicit phrases** (any of):
- "hand this off"
- "handoff doc"
- "summarize this for a new session"
- "compact this conversation"
- "I'm ending this session"
- "pick this up later"
- "wrap this up for tomorrow"
- "save this for the next session"

**Implicit signals** (no phrase, but the intent is unmistakable):
- User announces they're switching machines or stopping for the day mid-task
- Conversation context is growing long without a natural stopping point
- User says "let me come back to this" or "I'll continue this later"

When you detect an implicit trigger, propose the handoff before running it: *"Want me to write a handoff for the next session?"* — never run it silently.

## First-Run Setup

On first invocation, the skill asks where to save handoffs so the project folder never gets cluttered. Setup is offered once via *"Run setup now? (Y/n)"* — answering N uses OS-temp defaults for this run and never re-prompts. The user can rerun setup any time via `/cs-handoff-setup`.

See [references/configuration.md](references/configuration.md) for the full config field reference.

## Output Path

The save location is read from the user's config (`~/.config/handoff/config.json`, or the project-local `.handoff/config.json` if present). When no config exists and the user declined setup, fall back to:

```bash
mktemp -t handoff-XXXXXX.md
```

Read the file before you write to it.

## Section Template

The handoff doc has five sections. Use these exact headers:

- **Goal of next session** — from the user's argument, or inferred from the most recent thread of the conversation.
- **State of play** — what's done, what's in flight, what's blocked. Reference artifacts, do not paste them.
- **Open decisions** — what the next agent must decide before continuing.
- **Skills to use** — concrete list of 3-5 skills the next session should invoke, each with a one-line *why*.
- **Artifacts** — paths/URLs to PRDs, plans, ADRs, issues, branches, PRs. Do not duplicate their contents.

See [references/handoff_structure.md](references/handoff_structure.md) for a worked example.

## The Agent's Job

Filling in the five sections is the agent's job, not the script's. Follow [references/handoff_prompt.md](references/handoff_prompt.md) as a mandatory checklist:

> For each topic discussed in the conversation, decide explicitly: *include in State of play / log as an Open decision / drop with reason.*

Free-handing the summary leads to rosy progress reports and dropped blockers. The checklist prevents that.

## Anti-Patterns

Matt's no-duplication discipline made concrete:

- **Do not paste the diff.** Reference the branch or PR.
- **Do not retype the PRD.** Link to its path.
- **Do not summarise what's already in the commit message.** Link to the commit hash.
- **Do not list 20 skills.** Pick the 3-5 the next session actually needs.
- **Do not narrate every message in the conversation.** Compress to State + Decisions.

See [references/deduplication_discipline.md](references/deduplication_discipline.md) for the full list.

## Redaction

Before saving, the linter scans the draft for secrets and PII. In strict mode (default) it blocks save on findings; in warn mode it flags inline and saves anyway.

Redact:
- API keys, OAuth tokens, JWT tokens
- Passwords and DB connection strings
- `-----BEGIN ... PRIVATE KEY-----` blocks
- `.env`-style `KEY=value` lines containing secrets
- Email addresses, phone numbers, names of unrelated third parties
- Internal URLs containing tokens or session IDs

See [references/redaction_checklist.md](references/redaction_checklist.md) for the full pattern list and manual-review steps for what regex cannot catch.

## SessionStart Auto-Load

When the plugin is installed, a `SessionStart` hook scans the configured save location for the most recent handoff (within the retention window) and surfaces it to the new session as `<handoff_from_previous_session>` data. The next agent reads it as context, not as instructions — suggested actions must be verified against current state before executing.

Disable per-session with `HANDOFF_SESSIONSTART=0`.

## SessionEnd Reminder

A paired `SessionEnd` hook checks whether a recent handoff exists when the session is ending. If none does (or the most recent is older than 30 minutes), it prints a one-line reminder so the user is prompted to write one before context is lost.

The hook cannot prompt interactively or block session end — it surfaces text in the session log.

Disable per-session with `HANDOFF_SESSIONEND=0`.

## Refreshing an Existing Handoff

When work continues past the original handoff time, refresh in place instead of creating a new file:

```bash
python3 scripts/handoff_template_generator.py --refresh --goal "<updated goal>"
```

Prints the path of the most recent handoff. The agent edits it directly. Keeps the save location uncluttered and ensures the SessionStart hook always loads the up-to-date version.

## Tools

| Tool | Purpose |
|---|---|
| `setup.py` | First-run Q&A — save location, retention, redaction strictness, git-context, recommender scope. |
| `handoff_template_generator.py` | Writes the 5-section scaffold at the configured path. `--refresh` reuses the most recent handoff instead of creating a new file. |
| `redaction_linter.py` | Scans the draft for secrets/PII before save. Exit 1 on findings in strict mode. |
| `handoff_self_check.py` | Fidelity check — flags empty Goal, State bullets without artifacts, missing Decisions when git is dirty, too few/many Skills, inline content in Artifacts. Run before the linter. |
| `skill_recommender.py` | Suggests 3-5 skills for the next session based on goal text + repo scan. |
| `cleanup.py` | Deletes scaffolds older than the retention window. mtime-guarded — never deletes a handoff the user edited. |
| `config_loader.py` | Shared helper: read project config → global config → defaults. |

## Slash Commands

- `/cs-handoff [optional next-session description]` — generate the handoff.
- `/cs-handoff-setup` — reconfigure save location, retention, redaction.

## Agent

`cs-handoff-author` — Matt-voice persona orchestrating the skill. Terse, no-duplication, references-not-copies.

## Examples

### Example 1 — explicit invocation with a goal

```
User: /cs-handoff "finish wiring the redaction linter and open a draft PR"
```

The skill walks the mandatory checklist, generates a 5-section scaffold, fills it from the conversation, runs the redaction linter, and saves to the configured location. See `assets/example_handoff.md` for a complete worked example.

### Example 2 — implicit trigger

```
User: I'm packing up for the day, let me come back to this tomorrow.
```

Detect the implicit signal. Propose before running: *"Want me to write a handoff for the next session?"* — never silently. On confirmation, proceed as Example 1 with an inferred goal.

### Example 3 — first-run setup

```
User: /cs-handoff "ship the migration"
Skill: Run setup now? (Y/n)
User: Y
[setup walks 5 questions: save location, retention, redaction strictness, git context, recommender scope]
Skill: Config saved to ~/.config/handoff/config.json. Continuing with handoff for: ship the migration.
```

If the user answers N, the skill writes a sentinel and uses defaults (OS temp dir, 7-day retention, strict redaction). The prompt never re-appears.

### Example 4 — SessionStart auto-load

On the next session, the SessionStart hook scans the configured save location, finds the most recent handoff, and surfaces it as `<handoff_from_previous_session>` data. The next agent reads it as context, not instructions.

## Usage

| Step | Command |
|---|---|
| First-run setup | `/cs-handoff-setup` (or answer Y on first `/cs-handoff`) |
| Generate a handoff | `/cs-handoff [goal]` |
| Reconfigure later | `/cs-handoff-setup --reconfigure` |
| Project-specific config | `/cs-handoff-setup --project` |
| Disable SessionStart hook | `HANDOFF_SESSIONSTART=0` (per session) |

---

**Version:** 1.0.0
**Inspired by:** [Matt Pocock's handoff](https://github.com/mattpocock/skills/tree/main/skills/productivity/handoff) (MIT).

What will the next session be used for?

{
  "format": "aiskill/v1",
  "skill": {
    "name": "handoff",
    "slug": "handoff",
    "version": "1.0.0",
    "description": "Compact the current conversation into a handoff document for another agent to pick up. Save to a user-configured location (OS temp, home folder, or per-project .handoff/), redact secrets before write, suggest skills for the next session, and auto-load the latest handoff on the next SessionStart. First-run setup asks where to save so the project folder never gets cluttered. Use when the user says 'hand this off', 'handoff doc', 'summarize this for a new session', 'compact this conversation', 'I'm ending this session', 'pick this up later', or any variation signaling intent to pass work to a fresh agent. Also trigger on implicit signals: the user announcing they're switching machines, ending the day mid-task, or context is growing long without a natural stopping point.",
    "category": "Productivity",
    "tags": [
      "productivity",
      "security",
      "agents"
    ],
    "platforms": [
      "chatgpt",
      "claude-code",
      "cursor"
    ],
    "tested_environment": "Agent Skills convention (SKILL.md) — works with Claude Code, Cursor, ChatGPT/Codex and compatible agents",
    "license": "MIT"
  },
  "prompts": {
    "system": "# Handoff\r\n\r\nWrite a handoff document summarising the current conversation so a fresh agent can continue the work. Save to the temporary directory of the user's OS — not the current workspace.\r\n\r\nInclude a \"suggested skills\" section in the document, which suggests skills that the agent should invoke.\r\n\r\nDo not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.\r\n\r\nRedact any sensitive information, such as API keys, passwords, or personally identifiable information.\r\n\r\nIf the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.\r\n\r\n## Invocation Triggers\r\n\r\n**Explicit phrases** (any of):\r\n- \"hand this off\"\r\n- \"handoff doc\"\r\n- \"summarize this for a new session\"\r\n- \"compact this conversation\"\r\n- \"I'm ending this session\"\r\n- \"pick this up later\"\r\n- \"wrap this up for tomorrow\"\r\n- \"save this for the next session\"\r\n\r\n**Implicit signals** (no phrase, but the intent is unmistakable):\r\n- User announces they're switching machines or stopping for the day mid-task\r\n- Conversation context is growing long without a natural stopping point\r\n- User says \"let me come back to this\" or \"I'll continue this later\"\r\n\r\nWhen you detect an implicit trigger, propose the handoff before running it: *\"Want me to write a handoff for the next session?\"* — never run it silently.\r\n\r\n## First-Run Setup\r\n\r\nOn first invocation, the skill asks where to save handoffs so the project folder never gets cluttered. Setup is offered once via *\"Run setup now? (Y/n)\"* — answering N uses OS-temp defaults for this run and never re-prompts. The user can rerun setup any time via `/cs-handoff-setup`.\r\n\r\nSee [references/configuration.md](references/configuration.md) for the full config field reference.\r\n\r\n## Output Path\r\n\r\nThe save location is read from the user's config (`~/.config/handoff/config.json`, or the project-local `.handoff/config.json` if present). When no config exists and the user declined setup, fall back to:\r\n\r\n```bash\r\nmktemp -t handoff-XXXXXX.md\r\n```\r\n\r\nRead the file before you write to it.\r\n\r\n## Section Template\r\n\r\nThe handoff doc has five sections. Use these exact headers:\r\n\r\n- **Goal of next session** — from the user's argument, or inferred from the most recent thread of the conversation.\r\n- **State of play** — what's done, what's in flight, what's blocked. Reference artifacts, do not paste them.\r\n- **Open decisions** — what the next agent must decide before continuing.\r\n- **Skills to use** — concrete list of 3-5 skills the next session should invoke, each with a one-line *why*.\r\n- **Artifacts** — paths/URLs to PRDs, plans, ADRs, issues, branches, PRs. Do not duplicate their contents.\r\n\r\nSee [references/handoff_structure.md](references/handoff_structure.md) for a worked example.\r\n\r\n## The Agent's Job\r\n\r\nFilling in the five sections is the agent's job, not the script's. Follow [references/handoff_prompt.md](references/handoff_prompt.md) as a mandatory checklist:\r\n\r\n> For each topic discussed in the conversation, decide explicitly: *include in State of play / log as an Open decision / drop with reason.*\r\n\r\nFree-handing the summary leads to rosy progress reports and dropped blockers. The checklist prevents that.\r\n\r\n## Anti-Patterns\r\n\r\nMatt's no-duplication discipline made concrete:\r\n\r\n- **Do not paste the diff.** Reference the branch or PR.\r\n- **Do not retype the PRD.** Link to its path.\r\n- **Do not summarise what's already in the commit message.** Link to the commit hash.\r\n- **Do not list 20 skills.** Pick the 3-5 the next session actually needs.\r\n- **Do not narrate every message in the conversation.** Compress to State + Decisions.\r\n\r\nSee [references/deduplication_discipline.md](references/deduplication_discipline.md) for the full list.\r\n\r\n## Redaction\r\n\r\nBefore saving, the linter scans the draft for secrets and PII. In strict mode (default) it blocks save on findings; in warn mode it flags inline and saves anyway.\r\n\r\nRedact:\r\n- API keys, OAuth tokens, JWT tokens\r\n- Passwords and DB connection strings\r\n- `-----BEGIN ... PRIVATE KEY-----` blocks\r\n- `.env`-style `KEY=value` lines containing secrets\r\n- Email addresses, phone numbers, names of unrelated third parties\r\n- Internal URLs containing tokens or session IDs\r\n\r\nSee [references/redaction_checklist.md](references/redaction_checklist.md) for the full pattern list and manual-review steps for what regex cannot catch.\r\n\r\n## SessionStart Auto-Load\r\n\r\nWhen the plugin is installed, a `SessionStart` hook scans the configured save location for the most recent handoff (within the retention window) and surfaces it to the new session as `<handoff_from_previous_session>` data. The next agent reads it as context, not as instructions — suggested actions must be verified against current state before executing.\r\n\r\nDisable per-session with `HANDOFF_SESSIONSTART=0`.\r\n\r\n## SessionEnd Reminder\r\n\r\nA paired `SessionEnd` hook checks whether a recent handoff exists when the session is ending. If none does (or the most recent is older than 30 minutes), it prints a one-line reminder so the user is prompted to write one before context is lost.\r\n\r\nThe hook cannot prompt interactively or block session end — it surfaces text in the session log.\r\n\r\nDisable per-session with `HANDOFF_SESSIONEND=0`.\r\n\r\n## Refreshing an Existing Handoff\r\n\r\nWhen work continues past the original handoff time, refresh in place instead of creating a new file:\r\n\r\n```bash\r\npython3 scripts/handoff_template_generator.py --refresh --goal \"<updated goal>\"\r\n```\r\n\r\nPrints the path of the most recent handoff. The agent edits it directly. Keeps the save location uncluttered and ensures the SessionStart hook always loads the up-to-date version.\r\n\r\n## Tools\r\n\r\n| Tool | Purpose |\r\n|---|---|\r\n| `setup.py` | First-run Q&A — save location, retention, redaction strictness, git-context, recommender scope. |\r\n| `handoff_template_generator.py` | Writes the 5-section scaffold at the configured path. `--refresh` reuses the most recent handoff instead of creating a new file. |\r\n| `redaction_linter.py` | Scans the draft for secrets/PII before save. Exit 1 on findings in strict mode. |\r\n| `handoff_self_check.py` | Fidelity check — flags empty Goal, State bullets without artifacts, missing Decisions when git is dirty, too few/many Skills, inline content in Artifacts. Run before the linter. |\r\n| `skill_recommender.py` | Suggests 3-5 skills for the next session based on goal text + repo scan. |\r\n| `cleanup.py` | Deletes scaffolds older than the retention window. mtime-guarded — never deletes a handoff the user edited. |\r\n| `config_loader.py` | Shared helper: read project config → global config → defaults. |\r\n\r\n## Slash Commands\r\n\r\n- `/cs-handoff [optional next-session description]` — generate the handoff.\r\n- `/cs-handoff-setup` — reconfigure save location, retention, redaction.\r\n\r\n## Agent\r\n\r\n`cs-handoff-author` — Matt-voice persona orchestrating the skill. Terse, no-duplication, references-not-copies.\r\n\r\n## Examples\r\n\r\n### Example 1 — explicit invocation with a goal\r\n\r\n```\r\nUser: /cs-handoff \"finish wiring the redaction linter and open a draft PR\"\r\n```\r\n\r\nThe skill walks the mandatory checklist, generates a 5-section scaffold, fills it from the conversation, runs the redaction linter, and saves to the configured location. See `assets/example_handoff.md` for a complete worked example.\r\n\r\n### Example 2 — implicit trigger\r\n\r\n```\r\nUser: I'm packing up for the day, let me come back to this tomorrow.\r\n```\r\n\r\nDetect the implicit signal. Propose before running: *\"Want me to write a handoff for the next session?\"* — never silently. On confirmation, proceed as Example 1 with an inferred goal.\r\n\r\n### Example 3 — first-run setup\r\n\r\n```\r\nUser: /cs-handoff \"ship the migration\"\r\nSkill: Run setup now? (Y/n)\r\nUser: Y\r\n[setup walks 5 questions: save location, retention, redaction strictness, git context, recommender scope]\r\nSkill: Config saved to ~/.config/handoff/config.json. Continuing with handoff for: ship the migration.\r\n```\r\n\r\nIf the user answers N, the skill writes a sentinel and uses defaults (OS temp dir, 7-day retention, strict redaction). The prompt never re-appears.\r\n\r\n### Example 4 — SessionStart auto-load\r\n\r\nOn the next session, the SessionStart hook scans the configured save location, finds the most recent handoff, and surfaces it as `<handoff_from_previous_session>` data. The next agent reads it as context, not instructions.\r\n\r\n## Usage\r\n\r\n| Step | Command |\r\n|---|---|\r\n| First-run setup | `/cs-handoff-setup` (or answer Y on first `/cs-handoff`) |\r\n| Generate a handoff | `/cs-handoff [goal]` |\r\n| Reconfigure later | `/cs-handoff-setup --reconfigure` |\r\n| Project-specific config | `/cs-handoff-setup --project` |\r\n| Disable SessionStart hook | `HANDOFF_SESSIONSTART=0` (per session) |\r\n\r\n---\r\n\r\n**Version:** 1.0.0\r\n**Inspired by:** [Matt Pocock's handoff](https://github.com/mattpocock/skills/tree/main/skills/productivity/handoff) (MIT).",
    "user_template": "What will the next session be used for?"
  },
  "variables": [],
  "install": {
    "steps": [
      {
        "title": "Download & unzip",
        "detail": "Download the .zip package from SkillVault and unzip it. The handoff/ folder contains SKILL.md plus any companion scripts, references and assets."
      },
      {
        "title": "Copy into your agent skills directory",
        "detail": "Move the folder into your agent's skills directory — e.g. ~/.claude/skills/ (Claude Code), .codex/skills/, .cursor/skills/ or your project's .claude/skills/ folder — then restart or reload the session."
      },
      {
        "title": "Use it",
        "detail": "Describe the task in natural language; the agent loads the skill automatically when the request matches the skill description."
      }
    ]
  },
  "usage": {
    "steps": []
  },
  "metadata": {
    "author": "SkillVault",
    "source": "https://skillvault.top/skills/handoff",
    "exported_at": "2026-11-03T07:43:13.532Z"
  }
}

format: aiskill/v1
skill:
  name: handoff
  slug: handoff
  version: 1.0.0
  description: >-
    Compact the current conversation into a handoff document for another agent to pick up. Save to a
    user-configured location (OS temp, home folder, or per-project .handoff/), redact secrets before
    write, suggest skills for the next session, and auto-load the latest handoff on the next
    SessionStart. First-run setup asks where to save so the project folder never gets cluttered. Use
    when the user says 'hand this off', 'handoff doc', 'summarize this for a new session', 'compact
    this conversation', 'I'm ending this session', 'pick this up later', or any variation signaling
    intent to pass work to a fresh agent. Also trigger on implicit signals: the user announcing
    they're switching machines, ending the day mid-task, or context is growing long without a
    natural stopping point.
  category: Productivity
  tags:
    - productivity
    - security
    - agents
  platforms:
    - chatgpt
    - claude-code
    - cursor
  tested_environment: >-
    Agent Skills convention (SKILL.md) — works with Claude Code, Cursor, ChatGPT/Codex and
    compatible agents
  license: MIT
prompts:
  system: "# Handoff\r\n\r\nWrite a handoff document summarising the current conversation so a fresh agent can continue the work. Save to the temporary directory of the user's OS — not the current workspace.\r\n\r\nInclude a \"suggested skills\" section in the document, which suggests skills that the agent should invoke.\r\n\r\nDo not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.\r\n\r\nRedact any sensitive information, such as API keys, passwords, or personally identifiable information.\r\n\r\nIf the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.\r\n\r\n## Invocation Triggers\r\n\r\n**Explicit phrases** (any of):\r\n- \"hand this off\"\r\n- \"handoff doc\"\r\n- \"summarize this for a new session\"\r\n- \"compact this conversation\"\r\n- \"I'm ending this session\"\r\n- \"pick this up later\"\r\n- \"wrap this up for tomorrow\"\r\n- \"save this for the next session\"\r\n\r\n**Implicit signals** (no phrase, but the intent is unmistakable):\r\n- User announces they're switching machines or stopping for the day mid-task\r\n- Conversation context is growing long without a natural stopping point\r\n- User says \"let me come back to this\" or \"I'll continue this later\"\r\n\r\nWhen you detect an implicit trigger, propose the handoff before running it: *\"Want me to write a handoff for the next session?\"* — never run it silently.\r\n\r\n## First-Run Setup\r\n\r\nOn first invocation, the skill asks where to save handoffs so the project folder never gets cluttered. Setup is offered once via *\"Run setup now? (Y/n)\"* — answering N uses OS-temp defaults for this run and never re-prompts. The user can rerun setup any time via `/cs-handoff-setup`.\r\n\r\nSee [references/configuration.md](references/configuration.md) for the full config field reference.\r\n\r\n## Output Path\r\n\r\nThe save location is read from the user's config (`~/.config/handoff/config.json`, or the project-local `.handoff/config.json` if present). When no config exists and the user declined setup, fall back to:\r\n\r\n```bash\r\nmktemp -t handoff-XXXXXX.md\r\n```\r\n\r\nRead the file before you write to it.\r\n\r\n## Section Template\r\n\r\nThe handoff doc has five sections. Use these exact headers:\r\n\r\n- **Goal of next session** — from the user's argument, or inferred from the most recent thread of the conversation.\r\n- **State of play** — what's done, what's in flight, what's blocked. Reference artifacts, do not paste them.\r\n- **Open decisions** — what the next agent must decide before continuing.\r\n- **Skills to use** — concrete list of 3-5 skills the next session should invoke, each with a one-line *why*.\r\n- **Artifacts** — paths/URLs to PRDs, plans, ADRs, issues, branches, PRs. Do not duplicate their contents.\r\n\r\nSee [references/handoff_structure.md](references/handoff_structure.md) for a worked example.\r\n\r\n## The Agent's Job\r\n\r\nFilling in the five sections is the agent's job, not the script's. Follow [references/handoff_prompt.md](references/handoff_prompt.md) as a mandatory checklist:\r\n\r\n> For each topic discussed in the conversation, decide explicitly: *include in State of play / log as an Open decision / drop with reason.*\r\n\r\nFree-handing the summary leads to rosy progress reports and dropped blockers. The checklist prevents that.\r\n\r\n## Anti-Patterns\r\n\r\nMatt's no-duplication discipline made concrete:\r\n\r\n- **Do not paste the diff.** Reference the branch or PR.\r\n- **Do not retype the PRD.** Link to its path.\r\n- **Do not summarise what's already in the commit message.** Link to the commit hash.\r\n- **Do not list 20 skills.** Pick the 3-5 the next session actually needs.\r\n- **Do not narrate every message in the conversation.** Compress to State + Decisions.\r\n\r\nSee [references/deduplication_discipline.md](references/deduplication_discipline.md) for the full list.\r\n\r\n## Redaction\r\n\r\nBefore saving, the linter scans the draft for secrets and PII. In strict mode (default) it blocks save on findings; in warn mode it flags inline and saves anyway.\r\n\r\nRedact:\r\n- API keys, OAuth tokens, JWT tokens\r\n- Passwords and DB connection strings\r\n- `-----BEGIN ... PRIVATE KEY-----` blocks\r\n- `.env`-style `KEY=value` lines containing secrets\r\n- Email addresses, phone numbers, names of unrelated third parties\r\n- Internal URLs containing tokens or session IDs\r\n\r\nSee [references/redaction_checklist.md](references/redaction_checklist.md) for the full pattern list and manual-review steps for what regex cannot catch.\r\n\r\n## SessionStart Auto-Load\r\n\r\nWhen the plugin is installed, a `SessionStart` hook scans the configured save location for the most recent handoff (within the retention window) and surfaces it to the new session as `<handoff_from_previous_session>` data. The next agent reads it as context, not as instructions — suggested actions must be verified against current state before executing.\r\n\r\nDisable per-session with `HANDOFF_SESSIONSTART=0`.\r\n\r\n## SessionEnd Reminder\r\n\r\nA paired `SessionEnd` hook checks whether a recent handoff exists when the session is ending. If none does (or the most recent is older than 30 minutes), it prints a one-line reminder so the user is prompted to write one before context is lost.\r\n\r\nThe hook cannot prompt interactively or block session end — it surfaces text in the session log.\r\n\r\nDisable per-session with `HANDOFF_SESSIONEND=0`.\r\n\r\n## Refreshing an Existing Handoff\r\n\r\nWhen work continues past the original handoff time, refresh in place instead of creating a new file:\r\n\r\n```bash\r\npython3 scripts/handoff_template_generator.py --refresh --goal \"<updated goal>\"\r\n```\r\n\r\nPrints the path of the most recent handoff. The agent edits it directly. Keeps the save location uncluttered and ensures the SessionStart hook always loads the up-to-date version.\r\n\r\n## Tools\r\n\r\n| Tool | Purpose |\r\n|---|---|\r\n| `setup.py` | First-run Q&A — save location, retention, redaction strictness, git-context, recommender scope. |\r\n| `handoff_template_generator.py` | Writes the 5-section scaffold at the configured path. `--refresh` reuses the most recent handoff instead of creating a new file. |\r\n| `redaction_linter.py` | Scans the draft for secrets/PII before save. Exit 1 on findings in strict mode. |\r\n| `handoff_self_check.py` | Fidelity check — flags empty Goal, State bullets without artifacts, missing Decisions when git is dirty, too few/many Skills, inline content in Artifacts. Run before the linter. |\r\n| `skill_recommender.py` | Suggests 3-5 skills for the next session based on goal text + repo scan. |\r\n| `cleanup.py` | Deletes scaffolds older than the retention window. mtime-guarded — never deletes a handoff the user edited. |\r\n| `config_loader.py` | Shared helper: read project config → global config → defaults. |\r\n\r\n## Slash Commands\r\n\r\n- `/cs-handoff [optional next-session description]` — generate the handoff.\r\n- `/cs-handoff-setup` — reconfigure save location, retention, redaction.\r\n\r\n## Agent\r\n\r\n`cs-handoff-author` — Matt-voice persona orchestrating the skill. Terse, no-duplication, references-not-copies.\r\n\r\n## Examples\r\n\r\n### Example 1 — explicit invocation with a goal\r\n\r\n```\r\nUser: /cs-handoff \"finish wiring the redaction linter and open a draft PR\"\r\n```\r\n\r\nThe skill walks the mandatory checklist, generates a 5-section scaffold, fills it from the conversation, runs the redaction linter, and saves to the configured location. See `assets/example_handoff.md` for a complete worked example.\r\n\r\n### Example 2 — implicit trigger\r\n\r\n```\r\nUser: I'm packing up for the day, let me come back to this tomorrow.\r\n```\r\n\r\nDetect the implicit signal. Propose before running: *\"Want me to write a handoff for the next session?\"* — never silently. On confirmation, proceed as Example 1 with an inferred goal.\r\n\r\n### Example 3 — first-run setup\r\n\r\n```\r\nUser: /cs-handoff \"ship the migration\"\r\nSkill: Run setup now? (Y/n)\r\nUser: Y\r\n[setup walks 5 questions: save location, retention, redaction strictness, git context, recommender scope]\r\nSkill: Config saved to ~/.config/handoff/config.json. Continuing with handoff for: ship the migration.\r\n```\r\n\r\nIf the user answers N, the skill writes a sentinel and uses defaults (OS temp dir, 7-day retention, strict redaction). The prompt never re-appears.\r\n\r\n### Example 4 — SessionStart auto-load\r\n\r\nOn the next session, the SessionStart hook scans the configured save location, finds the most recent handoff, and surfaces it as `<handoff_from_previous_session>` data. The next agent reads it as context, not instructions.\r\n\r\n## Usage\r\n\r\n| Step | Command |\r\n|---|---|\r\n| First-run setup | `/cs-handoff-setup` (or answer Y on first `/cs-handoff`) |\r\n| Generate a handoff | `/cs-handoff [goal]` |\r\n| Reconfigure later | `/cs-handoff-setup --reconfigure` |\r\n| Project-specific config | `/cs-handoff-setup --project` |\r\n| Disable SessionStart hook | `HANDOFF_SESSIONSTART=0` (per session) |\r\n\r\n---\r\n\r\n**Version:** 1.0.0\r\n**Inspired by:** [Matt Pocock's handoff](https://github.com/mattpocock/skills/tree/main/skills/productivity/handoff) (MIT)."
  user_template: What will the next session be used for?
variables: []
install:
  steps:
    - title: Download & unzip
      detail: >-
        Download the .zip package from SkillVault and unzip it. The handoff/ folder contains
        SKILL.md plus any companion scripts, references and assets.
    - title: Copy into your agent skills directory
      detail: >-
        Move the folder into your agent's skills directory — e.g. ~/.claude/skills/ (Claude Code),
        .codex/skills/, .cursor/skills/ or your project's .claude/skills/ folder — then restart or
        reload the session.
    - title: Use it
      detail: >-
        Describe the task in natural language; the agent loads the skill automatically when the
        request matches the skill description.
usage:
  steps: []
metadata:
  author: SkillVault
  source: https://skillvault.top/skills/handoff
  exported_at: "2026-11-03T07:43:13.532Z"