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 agentmods add skills/sysangel/brain-mcp/handoffnpx skills add sysangel/brain-mcp --skill handoffgit clone --depth 1 https://github.com/sysangel/brain-mcpWrote 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/sysangel/brain-mcp/handoff)<a href="https://agentmods.dev/skills/sysangel/brain-mcp/handoff"><img src="https://agentmods.dev/badge/skills/sysangel/brain-mcp/handoff.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.00810 |
| Opus 5 | $0.00035 | $0.00405 |
| Sonnet 5 | $0.00014 | $0.00162 |
| Haiku 4.5 | $0.00007 | $0.00081 |
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 3d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
handoff
Session-state relay across /clear, for keeping sessions fresh without losing
the thread. Notes live in ~/src/brain/handoffs/ (git-tracked — text-in-git
rule; they will sync to a remote once git-sync ships, so write nothing you
wouldn't commit).
Mode selection
- Fresh session — this invocation is the first substantive message (right after /clear) → resume mode.
- Real work exists above in the conversation → write mode.
- Explicit args always win:
/handoff write,/handoff resume, or/handoff resume <topic or date>.
Write mode
- Distill THIS session into a briefing a context-free session can act on —
a briefing, not a transcript:
- Task — what we were working on and why.
- State — done / in-progress / blocked, with evidence (verdicts, test results, commits).
- Decisions — calls the user made this session. The next session must not re-litigate these.
- Next steps — the single concrete first action, then the ordered queue.
- Pointers — exact file paths, commands, branches, spec/doc locations.
- Open questions — only the genuinely unresolved.
- Get the timestamp (
date '+%Y-%m-%d-%H%M') and write to~/src/brain/handoffs/<timestamp>-<task-slug>.mdwith frontmatter:date(ISO),project(repo/dir the work lives in),description(one line). Names sort chronologically — that is the "latest" mechanism. - Commit:
git -C ~/src/brain add handoffs/ && git -C ~/src/brain commit -m "handoff: <task-slug>". - Tell the user the note is written and they can /clear. Then END the reply
with the exact kickoff for the next session in a fenced code block, so the
user can copy-paste it verbatim without thinking:
- default:
/handoff - if this note might not be the newest by then:
/handoff resume <task-slug> - if the next session should skip straight to a specific action, put that
full prompt in the block instead (e.g.
/handoffon one line, then the one-line instruction). The block is the deliverable of write mode — a handoff that doesn't tell the user what to paste next is incomplete.
- default:
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.
- 3d ago First seen · 64 lines · 70 tokens per session scan A 4a1822326aa2
handoff is a skill published in the GitHub repository sysangel/brain-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 810 once invoked, about $0.0003 per session on Opus 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
gno
Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…
check-memory-before-acting
Search this project's own memory before doing something it may already have opinions about. Use before running a build/test/deploy command, before choosing a library or approach, before changing configuration or CI, and before re-opening a decision that may already have been settled. Also use when a task resembles…
keep-memory-current
Load this project's memory when you start, and write back what you learned before you stop. Use at the beginning of a work session, when finishing a task or about to end a session, after debugging something non-obvious, after a decision that took argument to reach, and whenever you catch yourself thinking "I should…
kb-log
결정·삽질 즉시 기록 — 아키텍처/기술 결정을 내렸거나 버그의 원인을 규명한 "직후" 팀 지식베이스에 기록한다(recorddecision/recordlearning). kb MCP를 못 쓰는 상황(미연결, 서브에이전트)이면 .kb/ledger.jsonl 원장에 append해 유실을 막는다. "이 결정 기록해줘", "방금 삽질 남겨" 요청 시, 또는 중요한 결정·디버깅 완료 직후 자발적으로 사용.
kb-brief
작업 착수 브리핑 — 새 작업·이슈·버그 수정을 시작할 때 팀 지식베이스(kb MCP)에서 과거 함정(pitfalls), 관련 결정, 최근 변경, 담당자를 모아 착수 브리핑을 만든다. "X 작업 시작할게", "착수 전에 확인해줘", "관련 히스토리 찾아줘" 같은 요청이나 새 티켓/이슈에 착수할 때 사용.
agent-messaging
Send, poll, wait for, and acknowledge durable addressed agent-to-agent messages in Aionforge Memory (messagesend, messagepoll, messagewait, messageack) and subscribe to room resources. Use to hand a brief to another agent, page a teammate, wait for a reply, coordinate a multi-agent workflow, or drain an inbox …