Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mshadmanrahman/pm-pilot --skill handoff-docgit clone --depth 1 https://github.com/mshadmanrahman/pm-pilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mshadmanrahman/pm-pilot/handoff-doc)<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/handoff-doc"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/handoff-doc/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/handoff-doc"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/handoff-doc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00012 | $0.00491 |
| Opus 5.5 | $0.00005 | $0.00196 |
| Sonnet 5.5 | $0.00002 | $0.00098 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
handoff-doc scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Handoff Doc
Capture session state into a portable document for future sessions or other agents.
When to Use
- Ending a work session
- Switching to a different task or project
- Before context compaction
- Handing work to another person or agent
Procedure
-
Gather Context
- Review git log for commits made this session
- Review files modified (
git diff --name-onlyagainst session start) - Review any task updates in
tasks/todo.md - Review any lesson entries added to
tasks/lessons.md
-
Build Handoff Document Write to
.claude/handoffs/YYYY-MM-DD-session.md:--- date: {ISO 8601} project: {project name} --- # Session Handoff ## What Was Worked On - {bullet list of tasks/features touched} ## Decisions Made - {key decisions with rationale} ## Files Modified - {path}: {what changed} ## Open Questions - {unresolved questions} ## Blockers - {anything preventing progress, or "None"} ## Next Steps 1. {exact next action} 2. {follow-up action} -
Update Memory
- Add or update relevant entry in
MEMORY.mdif significant project state changed
- Add or update relevant entry in
-
Confirm
- Output path to handoff file
- Output one-line summary of session
Output Format
Handoff saved: .claude/handoffs/2026-03-14-session.md
Summary: Implemented CPL calculation, 2 open questions on data source.
Rules
- Use real datetime from
date -ucommand - Keep each section to 3-5 bullets max
- File paths must be relative (per path-standards rule)
- Never include secrets or credentials in handoff docs
- If multiple handoffs same day, append
-2,-3suffix
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 83 lines · 12 tokens per session scan A 38bc1c2c8203
handoff-doc is a skill published in the GitHub repository mshadmanrahman/pm-pilot (22 stars, last pushed 7d ago), licensed MIT. It adds 12 tokens to every session and 491 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
handoff-doc compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| handoff-docmshadmanrahman/pm-pilot | Skill | 22 | 7d ago | MIT | A | 12 | Claude Code |
| session-handoffchristopherlouet/claude-base | Skill | 5 | 6d ago | MIT | A | 33 | Claude Code |
| cloud-syncthedotmack/claude-mem | Skill | 114k | yesterday | Apache-2.0 | A | 64 | Claude Code |
| emerging-techniques-long-contextdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 78 | Claude Code, Codex |
| hive.note-takingaden-hive/hive | Skill | 11k | 4d ago | Apache-2.0 | A | 30 | Claude Code, Codex |
| vellum-memory-v3-migrationvellum-ai/vellum-assistant | Skill | 1.5k | 2d ago | MIT | A | 63 | Claude Code, Codex |
| memoryshobcoder/shob | Skill | 575 | 7d ago | MIT | A | 146 | Claude Code, Codex |