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 WrongStack/WrongStack --skill evidence-auditgit clone --depth 1 https://github.com/WrongStack/WrongStackWrote 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/wrongstack/wrongstack/evidence-audit)<a href="https://agentmods.dev/skills/wrongstack/wrongstack/evidence-audit"><img src="https://agentmods.dev/badge/skills/wrongstack/wrongstack/evidence-audit/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/wrongstack/wrongstack/evidence-audit"><img src="https://agentmods.dev/badge/skills/wrongstack/wrongstack/evidence-audit.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 | $0.00152 | $0.03495 |
| Opus 5.5 | $0.00061 | $0.01398 |
| Sonnet 5.5 | $0.00030 | $0.00699 |
| Haiku 4.5 | $0.00015 | $0.00349 |
Grade A, and why
evidence-audit 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 5d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence-led audit
Invoke as $evidence-audit <scope>. The text after the skill name is the scope. Every round produces the same thing: a ledger of findings where each finding has a proof that fails on current code, a patch that touches only the scope, and a verifier that passes after the patch. Nothing without a proof becomes a patch. Nothing without a verifier is called fixed. This holds in every language and every repo: an unproven "improvement" is a regression risk with no upside.
Selection card
- Task: Find, prove, fix and independently verify real defects.
- Start: Identify the scope and obtain an executable before-proof or review evidence.
- Finish: apply the acceptance checks below; report observed results and unresolved constraints.
Setup (every round, before any analysis)
- Read the repo's agent instructions if present (
AGENTS.md,CONTRIBUTING.md, or equivalent at the root and in the scope). Rungit status --shortand record the output: these are pre-existing changes you must preserve and never touch. - Detect the toolchain from the repo, not from assumptions. Record, with the file that proves each: language(s) and version, package/build tool, test runner and how the project invokes it, type checker (if any), formatter/linter, and whether a race detector, sanitizer, or coverage tool is already configured. Use only what is already there. Do not install a test framework, mutation tool, or linter.
- Resolve the scope. A scope is concrete when it maps to specific files. If the prompt gives none, or it is vague ("the backend", "everything"):
- Do a shallow structural scan only: directory layout, entry points, modules with thin or no tests, recent churn from
git log --stat -20. Do not read implementations in depth yet. - List 5–8 numbered candidate scopes, each with path(s), one line on what it does, and one line on why it is risky (concurrency, I/O, error handling, no tests, recent churn, many callers).
- Ask the user to pick a number or give a path, print
Awaiting scope., and stop. Do not choose for them.
- Do a shallow structural scan only: directory layout, entry points, modules with thin or no tests, recent churn from
- Print
Scope confirmed: <paths>. Everything you patch must be inside it. Files outside may be read for callers, types, and configs only. - If
.temp_files/ledger_<scope-slug>.mdalready exists, this is a continued round: read it, keep its IDs, start new findings from the next free ID. Never renumber. - Read the scope's source and its nearest tests before forming any candidate. Write down the invariants the code is supposed to keep: what must be true after each await/yield/callback, who owns each resource, what state a caller may observe mid-operation, which inputs are trusted. Real defects are violations of invariants the author assumed but never checked.
What ships with it
1 file 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.
- 5d ago Changed 33aec1af95e0
- 6d ago Changed · +23 lines 5acabe738089
- 11d ago First seen · 151 lines · 152 tokens per session scan A 4621cec09114
evidence-audit is a skill published in the GitHub repository WrongStack/WrongStack (376 stars, last pushed today), licensed MIT. It adds 152 tokens to every session and 3,495 once invoked, about $0.0006 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 2026-10-05.
Other skills, from other repositories
systematic-debugging
Find the root cause before proposing any fix. Use when something fails, throws, hangs, flakes, or behaves unexpectedly, including failing tests and CI. Auto-activates for bug reports.
claim-check
Claim checker that audits a coding agent's statements that tests pass or a build is clean against its own session transcripts: whether a matching run happened before the claim, whether it passed, and whether code changed after it. Use when the user asks whether the agent really ran the tests, how often it said tests…
backpropagation
Trace runtime bugs back to spec gaps — identify missing acceptance criteria, update specs, generate regression tests, and detect patterns.
investigate
Root-cause a bug, test failure, CI failure, or unexpected behavior before changing code. Reproduce, compare against working code, test one hypothesis at a time, then fix with a failing regression test first. Stops after three failed fixes to question the design, and requires fresh evidence before any "fixed" claim.…
validate
Validate the current diff for correctness bugs and test-integrity regressions (a test weakened to pass is a defect); supports --effort low|medium|high|max, --full to scan the whole repo, --fix to apply fixes, --comment to post as PR inline comments.
chaos-fault-injection
Deliberately inject faults — dropped connections, corrupted writes, latency, malformed responses, resource exhaustion — and assert the system's expected recovery (escalation, hardstop, rollback).