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 artifact-evidence-gategit 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/artifact-evidence-gate)<a href="https://agentmods.dev/skills/45ck/skill-harness/artifact-evidence-gate"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/artifact-evidence-gate/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/artifact-evidence-gate"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/artifact-evidence-gate.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 | $0.00021 | $0.00238 |
| Opus 5.5 | $0.00008 | $0.00095 |
| Sonnet 5.5 | $0.00004 | $0.00048 |
| Haiku 4.5 | $0.00002 | $0.00024 |
Grade A, and why
artifact-evidence-gate 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 1mo 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
Artifact Evidence Gate
Use this skill before treating a developer artifact as ready for handoff, review, or implementation.
Checks
- The artifact has a clear purpose and owner.
- The canonical source is named.
- Generated views link back to source.
- Source-backed generated views are listed in
docs/artifacts/artifacts.manifest.jsonwhen the project uses the scaffold. - Evidence is concrete: files, issues, tests, screenshots, logs, traces, or citations.
- Claims are separated from assumptions.
- Stale generated outputs are identified.
- HTML artifacts contain no secrets and no external script or asset dependency unless explicitly approved.
Verdicts
ready- evidence and source links are sufficient.needs-source- generated view exists but canonical source is missing or stale.needs-evidence- claims are under-supported.unsafe- artifact leaks sensitive data or executes unapproved code/network behavior.
Output
Verdict
Blocking Gaps
Evidence Present
Required Fixes
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.
- 1mo ago First seen · 35 lines · 21 tokens per session scan A 80e4b884e378
artifact-evidence-gate is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 238 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
do-it-audit
Use when the user explicitly requests a deep repository or scoped audit; not for ordinary diff review.
do-it-review
Use to assess requirements and implementation quality independently, or to resolve a batch of review findings.
pull-request-feedback
Use when working through review feedback on a GitHub pull request — reading review and inline comments one by one, discussing and making changes, replying or reacting, then pushing and re-requesting review. Trigger on "review the PR feedback", "go through the comments", "address review feedback".
interactive-review
Use when a skill needs the user to interactively review code changes in Hunk mid-workflow — working changes, staged changes, or a specific commit — then act on their decision and comments. Takes a review mode.
pre-review
Use when a commit's changes are finished and about to be presented for review. Runs the checks that catch the objections the user would otherwise raise, before they spend time reviewing.
enable-review
Turn interactive commit reviews back on for the current herdr workspace.