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 44-pixels/handover-mcp --skill handover-resumegit clone --depth 1 https://github.com/44-pixels/handover-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/44-pixels/handover-mcp/handover-resume)<a href="https://agentmods.dev/skills/44-pixels/handover-mcp/handover-resume"><img src="https://agentmods.dev/badge/skills/44-pixels/handover-mcp/handover-resume/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/44-pixels/handover-mcp/handover-resume"><img src="https://agentmods.dev/badge/skills/44-pixels/handover-mcp/handover-resume.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 | $0.00062 | $0.00737 |
| Opus 5 | $0.00031 | $0.00368 |
| Sonnet 5 | $0.00012 | $0.00147 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
handover-resume 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 9d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume context from Handover
Continue the canonical record instead of reconstructing work from a transcript.
Requires a configured Handover MCP connection or the handover-sh CLI with an
authenticated Handover identity.
Select the interface
Prefer Handover MCP tools. Fall back to the handover CLI. If neither is
configured, direct the user to
https://handover.sh/install?utm_source=agent_skill&utm_medium=workflow&utm_campaign=handover_resume_skill.
Verify identity and scope
- MCP: call
handover.whoami. - CLI: run
handover whoami --json.
Confirm the intended account and workspace before searching. An empty result can be correct when the identity lacks access; do not bypass it with a copied URL, author name, or organization parameter.
Use only the smallest workspace scope needed for the requested record. Never print, copy into artifacts, or ask the user to paste credentials or tokens. If access is denied, preserve the boundary and report it instead of switching to a broader identity.
Resolve the canonical record
- If given a Handover URL, slug, or identifier, open that exact record.
- Otherwise search distinctive nouns, identifiers, filenames, and decisions
with
handover.searchorhandover search "<query>" --json. - When several records match, prefer the active canonical record with the newest relevant revision. Ask before choosing when intent remains ambiguous.
- Read the current revision, artifacts, thread, and open annotations.
- Download or read original artifacts needed to verify claims.
With the CLI:
handover show <handover-id> --json
handover pull <slug-or-url> --out <directory> --json
Produce a resume brief
Before acting, state:
- objective;
- verified current state;
- decisions already made;
- evidence inspected;
- unresolved annotations and assignments;
- constraints and risks;
- next action;
- current revision identifier.
Clearly label assumptions and missing evidence.
Continue safely
Use handover.continue with the current expectedRevisionId. This optimistic
concurrency check prevents overwriting another actor's newer work.
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.
- 9d ago First seen · 100 lines · 62 tokens per session scan A a31b64509570
handover-resume is a skill published in the GitHub repository 44-pixels/handover-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 737 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
pensieve
The user's personal Pensieve memory — a persistent, self-organising knowledge base that survives across sessions. Use whenever the user mentions "pensieve", asks about "my streams" / "my memory" / "what have I saved", says "add this to pensieve" / "remember this" / "save this", asks "what do I know about ", or wants…
pensieve
Use the user's persistent Pensieve memory when they explicitly ask to save, remember, recall, resume, or inspect durable personal context, including requests mentioning Pensieve, streams, or saved memory. Do not invoke merely because a conversation contains potentially useful information.
handoff
Generate a passoff package so the next reader can pick up cleanly — for future-you in a new session (typically when context is high and you need to restart) or for a coworker (via brief mode). Default + auto modes emit a paste-ready next-session opener as the headline artifact, alongside PROGRESS / CLAUDE / memory…
audit-share
Batch-review personal knowledge for promotion to team-shared project knowledge. Walks insights/decisions/approaches/rules and IDEAS-BACKLOG.md entries, recommends a target project-knowledge/ destination per item, and lets the user approve all/numbers/modify/skip. Use when user says '/audit-share', '/share-audit'…
wrapup
Close out a session cleanly when the work is done — no passoff intended. Reviews session work, updates PROGRESS.md / CLAUDE.md / memory, commits changes, captures session knowledge via /extract, and confirms everything is wrapped up, captured, and documented. Use when the task is complete and nothing needs to carry…
context
Load relevant knowledge by topic. Queries the tag index and presents matching promoted files for selective loading into context. Use when user says '/context stripe', '/context api pagination', '/context ss', 'load knowledge about...', 'what do we know about...'. (Code port — ADR-094.).