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 45ck/skill-harness --skill skill-provenance-reviewergit clone --depth 1 https://github.com/45ck/skill-harnessWrote 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/45ck/skill-harness/skill-provenance-reviewer)<a href="https://agentmods.dev/skills/45ck/skill-harness/skill-provenance-reviewer"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/skill-provenance-reviewer/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/45ck/skill-harness/skill-provenance-reviewer"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/skill-provenance-reviewer.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 | $0.00036 | $0.00293 |
| Opus 5 | $0.00018 | $0.00147 |
| Sonnet 5 | $0.00007 | $0.00059 |
| Haiku 4.5 | $0.00004 | $0.00029 |
Grade A, and why
skill-provenance-reviewer 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 12d 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.
What it actually says
Skill Provenance Reviewer
Use this skill before a public or generated skill becomes a first-party harness asset, fixture, or downstream install surface.
Process
- Identify the source repo, owner, commit or release, license, and whether the license covers the specific copied content.
- Separate protected expression from reusable ideas, formats, and behavior.
- Inspect helper scripts, package manifests, MCP configs, plugin manifests, and install instructions for side effects.
- Flag user-global writes, credential handling, shell pipelines, postinstall hooks, network calls, destructive commands, approval bypass, sandbox disabling, and secret exposure patterns.
- Decide whether the material can be copied with attribution, must be rewritten, should become a fixture only, or should be rejected.
- Record attribution and provenance requirements for anything copied or adapted.
Output
Source
License Position
Copied Or Rewritten Content
Tool And Script Surfaces
Permission Risks
Required Attribution
Adoption Decision
Evidence
Avoid
- relying on repo popularity as a trust signal
- assuming a repo-wide license covers every embedded asset
- burying MCP or plugin permissions inside implementation detail
- approving generated or recorded skills without provenance and redaction review
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.
- 12d ago First seen · 36 lines · 36 tokens per session scan A 918b4e370276
skill-provenance-reviewer is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 293 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
do-it-architecture
Use when authority, ownership, contracts, dependency boundaries, migration, recovery, or structural deletion can change a design.
do-it-code-quality
Use when designing, changing, or debugging code to locate causal ownership and close the affected behavior.
do-it-core
Use when repository work needs a shared baseline for intent, facts, causal changes, and honest evidence.
do-it-decide
Use when uncertainty about a choice, plan, dependency, or handoff could materially change what gets built.
do-it-review
Use to assess requirements and implementation quality independently, or to resolve a batch of review findings.
do-it-skill-authoring
Use when creating or revising a do-it skill so its trigger and unique professional judgment are useful without prescribing ceremony.