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 instructions/snapsynapse/skill-provenance/agents-mdgit clone --depth 1 https://github.com/snapsynapse/skill-provenanceWhat 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 | $0.01120 | $0.01120 |
| Opus 5 | $0.00560 | $0.00560 |
| Sonnet 5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
skill-provenance AGENTS.md 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents Guide
Instructions for AI agents (Claude, Codex, Gemini CLI, etc.) working on this repository. This metaskill is also published to ClawHub for discovery by OpenClaw agents.
Repository structure
skill-provenance/ ← Canonical source bundle (DO NOT rename)
├── SKILL.md ← Agent-facing skill definition
├── README.md ← Human-facing user guide (has internal version header)
├── MANIFEST.yaml ← File inventory: roles, versions, SHA-256 hashes
├── CHANGELOG.md ← Recent in-bundle change history (last 5 entries)
├── evals.json ← 41 core evaluation scenarios
├── evals-distribution.json ← 18 supplemental distribution evals
├── validate.sh ← Bash script for local hash verification
├── package.sh ← Bash script for derived strict/ClawHub outputs
└── references/standalone-verification.md ← No-plugin verify/bootstrap path
action.yml ← GitHub Actions Marketplace wrapper for validate.sh
verify.sh ← Standalone wrapper pinned to canonical validate.sh
CHANGELOG.md ← Full append-only repo history
skill-provenance.skill ← Claude Settings ZIP (rebuilt from the directory)
The skill-provenance/ directory is the single source of truth. The .skill file is a packaging wrapper.
Before making changes
- Read
skill-provenance/MANIFEST.yamlto understand the current bundle state. - Run
./skill-provenance/validate.shto confirm all hashes are clean. - Read
skill-provenance/CHANGELOG.mdfor recent context and rootCHANGELOG.mdif you need older release history.
After making changes
- Bump per-file
versionintegers inMANIFEST.yamlfor every file you changed. - Recompute hashes: run
./skill-provenance/validate.sh --update. - Bump
bundle_version(semver) inMANIFEST.yaml:- PATCH for docs, typos, non-functional changes.
- MINOR for new features, new files, capability additions.
- MAJOR for breaking changes to the versioning model or spec.
- Update
bundle_dateto today. - Add a new entry at the top of both changelogs:
skill-provenance/CHANGELOG.mdkeeps the newest 5 entries only.CHANGELOG.mdat repo root is the full append-only archive. Name every file that changed and describe what changed in each.
- Rebuild the
.skillZIP if bundle contents changed:rm -f skill-provenance.skill zip -r skill-provenance.skill skill-provenance/ - Run
./.github/scripts/release-surface-check.shto confirm eval-count declarations, the standalone validator pin, GuideCheck sidecar metadata, and the.skillZIP all match the current source.
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 · 97 lines · 1,120 tokens per session scan A e13120288b0d
skill-provenance AGENTS.md is an instructions file published in the GitHub repository snapsynapse/skill-provenance (7 stars, last pushed 5d ago), licensed MIT. It adds 1,120 tokens to every session, about $0.0056 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 instructions, from other repositories
antigravity-claude-proxy CLAUDE.md
Instructions for badrisnarayanan/antigravity-claude-proxy, covering claude.md, commands and non-obvious things.
agentic-workflow CLAUDE.md
Instructions for gtrabanco/agentic-workflow, covering claude.md, repository layout, working rules, authoring a skill and hand off, don't compose across a model/effort boundary.
agentic-workflow AGENTS.md
Instructions for gtrabanco/agentic-workflow: All guidance for AI coding agents working in this repository lives in CLAUDE.md.
ccproxy AGENTS.md
AGENTS.md instructions for starbaser/ccproxy, covering claude.md, project overview, cross-project documentation — first-party stack, commands and cli.
EduOrchestrate AGENTS.md
Instructions for haroontrailblazer/EduOrchestrate, covering eduorchestrate agent instructions, command and workflow.
EduOrchestrate GEMINI.md
Instructions for haroontrailblazer/EduOrchestrate: Use /eduorchestrate as the learner command. When invoked, load the EduOrchestrate workflow and its prebuilt terminal-card program; never recreate, type out, or hand-design the card UI in the agent prompt. Ask for missing learner profile details, ask what the learner…