Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add rjmurillo/ai-agents/plugin install project-toolkitWrote 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/rjmurillo/ai-agents/evidence-provenance)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/evidence-provenance"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/evidence-provenance/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/rjmurillo/ai-agents/evidence-provenance"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/evidence-provenance.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 | $0.00112 | $0.01697 |
| Opus 5.5 | $0.00045 | $0.00679 |
| Sonnet 5.5 | $0.00022 | $0.00339 |
| Haiku 4.5 | $0.00011 | $0.00170 |
Grade A, and why
evidence-provenance 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 4d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Provenance
A second artifact is not a second proof. Count loops, not files.
Owns one invariant: evidence produced by the same reasoning loop as the artifact it validates is one evidentiary loop, unless something outside that loop can falsify it. It does not reject creator-authored tests, require a human reviewer, require several models, or force an expensive or unavailable gate.
Triggers
is this independent evidence, did the reviewer confirm this, closed loop,
count the confirmations, which checks actually ran
The invariant
agent reads requirement R
+--> writes implementation I
+--> writes new test T from the same reading
I + T = useful evidence about I
I + T != two independent confirmations of R
Creator tests stay valid. They answer "does I do what I was written to do". They cannot answer "was R read correctly", because both artifacts inherit one reading.
Process
-
List the claim and the artifact. Name the artifact, its revision, and the premises it was built from (the reading of R, the generator, the fixture source).
-
Record each piece of evidence with its lineage. The fields and their values are in
references/lineage-model.md. Two rules decide most cases:- Shared premise or inheritance joins the subject's loop. A reviewer who is handed the implementer's conclusion, or an expected output made by the implementation's generator, is in that loop whatever agent produced it.
- Lineage you cannot state is lineage you cannot count. An item with no recorded premises is never independent.
-
Classify. Write the record as JSON and run:
python3 "${COPILOT_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-.claude}}/skills/evidence-provenance/scripts/classify_lineage.py" <record.json>An item whose
bound_tonames a different artifact or revision is always rejected (binding-mismatch), not downgraded. Add--promotionwhen the evidence gates a deployment: every item then also needs abound_towith artifact, revision, validator, command, and result, or it is rejected asbinding-missing. -
Read the verdict.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 151 lines · 112 tokens per session scan A 6f5eb45b46d2
evidence-provenance is a skill published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 112 tokens to every session and 1,697 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 2026-10-14.
Other skills, from other repositories
architecture-audit
Comprehensive project consistency review across code, documentation, diagrams, and configuration.
code-review
Systematic code review for correctness, security, and growth — not just style enforcement.
semantic-codebase-intelligence
Deep structural analysis of a codebase—dependency mapping, architecture boundary detection, coupling/cohesion scoring, and dead code discovery. Use when asked to "analyze codebase structure", "map dependencies", "find dead code", "architecture analysis", "coupling analysis", "trace dependencies", or "understand this…
deep-review
Adversarial code review with three parallel perspectives — Advocate, Skeptic, Architect — that create productive tension. Use for high-stakes PRs, architectural changes, or when single-pass review would miss issues. Surfaces findings through disagreement, not consensus.
extension-audit-methodology
Systematic 5-dimension audit framework for VS Code extensions — debug hygiene, dead code, performance, menu validation, dependency cleanup.
parity-guard-test-pattern
When checking that all callers of a contract implement it correctly, you get false positives from wrapper delegators.