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 randommonicle/claude-skills --skill findings-are-evidencegit clone --depth 1 https://github.com/randommonicle/claude-skillsWrote 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/randommonicle/claude-skills/findings-are-evidence)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/findings-are-evidence"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/findings-are-evidence/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/randommonicle/claude-skills/findings-are-evidence"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/findings-are-evidence.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 | $0.00111 | $0.00726 |
| Opus 5 | $0.00056 | $0.00363 |
| Sonnet 5 | $0.00022 | $0.00145 |
| Haiku 4.5 | $0.00011 | $0.00073 |
Grade A, and why
findings-are-evidence 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Findings are evidence
Ten incidents across two repos of acting on an overstated, stale, or simply wrong claim that arrived wearing a severity label: a "critical" shared-phone exploit refuted by reading the installed dependency's source; a reviewer's suggested correction that was itself wrong on the statute; a scout asserting a directory did not exist when it did; a verifier "blessing" a wrong claim because the brief it was handed contained the error. Layer: one of the six always-on norms; this file is the playbook.
The rule
Reports are inputs to verification, not outputs of it. Before a claim gates a merge, enters a durable artifact, or triggers work: re-derive it from the primary source if it is rated Critical or High, touches a regulatory anchor, or is your own analysis of a defect or fix.
How to apply
- A severity label is a hypothesis. Before gating anything on a "Blocker", refute it
against ground truth — the installed
node_modulessource, the live catalog, the actual runtime — not against the reporter's confidence. - The brief handed to a verifier is itself a claim. A verification pass inherits its brief's errors; a specialist contradicting the brief earns a primary-source check, not an override.
- Your own conclusions qualify. Verify the claim you make about the FIX, not just the claim you were given — the remedy's reasoning earns its own verification pass.
- A failure message is a symptom, not a diagnosis ("not recognized" is not "not installed"). This is the canonical home of that rule; verified-citations cross-references it.
- A convenience tool that mirrors a first-party CLI must be diffed against the CLI before its output is committed — an MCP typegen once emitted a 483-line-short file that passed every gate. Prefer the path the project's own scripts drive.
- A wrong exploit can still sit on a real smell. Fix what is real; drop the inflated severity. Refutation is not exoneration.
What this skill does not do
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 · 52 lines · 111 tokens per session scan A 8e2fe5e32c77
findings-are-evidence is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 6d ago), licensed Apache-2.0. It adds 111 tokens to every session and 726 once invoked, about $0.0006 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…