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 Angel45604/the-foreman --skill handoffgit clone --depth 1 https://github.com/Angel45604/the-foremanWrote 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/angel45604/the-foreman/handoff)<a href="https://agentmods.dev/skills/angel45604/the-foreman/handoff"><img src="https://agentmods.dev/badge/skills/angel45604/the-foreman/handoff/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/angel45604/the-foreman/handoff"><img src="https://agentmods.dev/badge/skills/angel45604/the-foreman/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00143 | $0.01872 |
| Opus 5.5 | $0.00057 | $0.00749 |
| Sonnet 5.5 | $0.00029 | $0.00374 |
| Haiku 4.5 | $0.00014 | $0.00187 |
Grade A, and why
handoff 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 28d 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
handoff — teach the next agent (cold-start handoff + kickoff prompt)
The next agent starts with zero context. Your job is not to summarize — it's to transmit enough that a fresh agent resumes as if it were you: the same understanding of the work, the same git/verification footing, and the same development workflow (skills, posture, hard-won gotchas).
You produce two artifacts at two altitudes, and they are different on purpose:
| Artifact | Altitude | Audience | Filename (default) |
|---|---|---|---|
| Handoff doc | deep, exhaustive | the fresh agent reads it cold | handoff-<YYYY-MM-DD>-<slug>.md |
| Kickoff prompt | lean, paste-ready | the user pastes it into the fresh agent | next-agent-prompt-<YYYY-MM-DD>-<slug>.md |
The kickoff prompt points at the handoff doc — it never duplicates it. The user copies the kickoff prompt in one action; the fresh agent then reads the doc for the full picture.
Step 1 — Gather ground truth (never write a handoff from memory)
A handoff is a pile of claims about state. A wrong claim sends the fresh agent down the wrong path for an hour. Anchor everything in evidence before you write a word:
- Git state — run
git status -sb,git log --oneline -8,git branch --show-current,git rev-parse HEAD. Capture: branch, exact HEAD sha, clean vs dirty, staged vs unstaged, pushed vs local-only, and anything that must never be staged (scratch, design bundles, dev hacks). - Verification — list the test / lint / build commands this work uses and their last actual result. Tag each ✅ verified this session vs ⬜ assumed. Never mark work DONE that you didn't watch pass — an honest "in-flight, unverified" beats a confident lie.
- Where the work lives — the active plan/bundle dir (
docs/plans/active/...), the key files aspath:line, the auto-memory entry if the project uses one. - The conversation — distill: the goal + why, decisions already made, gotchas discovered, what's DONE+verified, what's in-flight, and the exact next steps in order.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 28d ago Changed · +1 lines 57abcb5e7dc2
- 2mo ago First seen · 112 lines · 143 tokens per session scan A 7c572eed5098
handoff is a skill published in the GitHub repository Angel45604/the-foreman (2 stars, last pushed 6d ago), licensed MIT. It adds 143 tokens to every session and 1,872 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.