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 snapsynapse/skill-provenance --skill handoffgit clone --depth 1 https://github.com/snapsynapse/skill-provenanceWrote 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/snapsynapse/skill-provenance/handoff)<a href="https://agentmods.dev/skills/snapsynapse/skill-provenance/handoff"><img src="https://agentmods.dev/badge/skills/snapsynapse/skill-provenance/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/snapsynapse/skill-provenance/handoff"><img src="https://agentmods.dev/badge/skills/snapsynapse/skill-provenance/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 | $0.00093 | $0.00677 |
| Opus 5.5 | $0.00037 | $0.00271 |
| Sonnet 5.5 | $0.00019 | $0.00135 |
| Haiku 4.5 | $0.00009 | $0.00068 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Provenance: Handoff
Generate a structured handoff note that captures project state for the next session or a collaborator picking up the work.
When to use
Run /skill-provenance:handoff when:
- Crossing a non-persistent boundary (e.g., uploading to Claude Chat where filesystem state won't carry over).
- The session made significant decisions not yet reflected in files.
- The user explicitly asks for a handoff note.
- A collaborator or future session needs context beyond what the manifest and changelog provide.
When NOT to use: In filesystem-native environments (Claude Code, IDE) with a current manifest, changelog, and git history, a handoff note is usually unnecessary. The manifest and changelog are the handoff.
Protocol
-
Read current state. Load
MANIFEST.yamlandCHANGELOG.mdto understand the bundle's current version and recent history. -
Generate the handoff note with these sections:
- Current bundle version — name and semver from the manifest.
- What was accomplished this session — summarize the work done, not just files changed.
- What is stale and needs attention — files flagged as behind or not updated this session.
- What the next session should do first — concrete first action, not vague guidance.
- Decisions made but not yet reflected in files — architecture choices, deferred items, scope decisions that someone reading only the code wouldn't know about.
- Per-file change summaries — for each file modified this session, a brief description of what changed (section added, field removed, logic rewritten). More granular than the changelog entry; helps the next session verify work without re-reading every file.
-
Replace, don't accumulate. A new handoff note replaces the previous one. Previous handoffs live in changelog history. Don't maintain a chain of handoff files.
-
Placement. Write the handoff note as a markdown file in the bundle directory (e.g.,
HANDOFF.md). Track it in the manifest withrole: handoffif the user wants it to persist across sessions.
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 · 72 lines · 93 tokens per session scan A 2df117cc337d
handoff is a skill published in the GitHub repository snapsynapse/skill-provenance (7 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 677 once invoked, about $0.0004 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
cocoplus-off
Deactivate Full Assist Mode — removes all CocoPlus feature flags. Data files (memory, meter history, grove patterns) are preserved. Idempotent.
cocoplus-on
Activate Full Assist Mode — enables all CocoPlus features simultaneously: Memory Engine, Environment Inspector, Safety Gate (normal), Code Quality Advisor, Context Mode, and CocoMeter. Also triggers a background environment scan. Idempotent.
wisdom-forget
Remove a must-keep CocoWisdom entry with rationale. Usage: $wisdom forget --id --rationale " ".
daily-life-discovery
Guide a consent-based conversation that helps a person discover how an AI agent could improve their day-to-day life: routines, friction, attention, decisions, relationships, learning, and small experiments. Use when someone asks for a daily check-in, wants the agent to learn how they work, says "grill me," wants a…
notion
Operate Notion from a terminal or agent: retrieve pages, query databases, search pages and databases, and update page properties — with a bundled notion-cli script that is read-only by default and gates every create or update behind a --dry-run/--yes confirmation. Use when an agent needs to read Notion content, answer…
slack
Operate Slack workspaces from a terminal or agent: list channels, read messages, follow threads, search message history, list files, and verify inbound webhook signatures — with a bundled slack-cli script that is read-only by default and gates every send behind a --dry-run/--yes confirmation. Use when an agent needs…