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 dwarvesf/dwarves-kit --skill gauntlet-proof-auditgit clone --depth 1 https://github.com/dwarvesf/dwarves-kitWrote 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/dwarvesf/dwarves-kit/gauntlet-proof-audit)<a href="https://agentmods.dev/skills/dwarvesf/dwarves-kit/gauntlet-proof-audit"><img src="https://agentmods.dev/badge/skills/dwarvesf/dwarves-kit/gauntlet-proof-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/dwarvesf/dwarves-kit/gauntlet-proof-audit"><img src="https://agentmods.dev/badge/skills/dwarvesf/dwarves-kit/gauntlet-proof-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 | $0.00105 | $0.02130 |
| Opus 5.5 | $0.00042 | $0.00852 |
| Sonnet 5.5 | $0.00021 | $0.00426 |
| Haiku 4.5 | $0.00011 | $0.00213 |
Grade A, and why
gauntlet-proof-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 2d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gauntlet proof-audit
Overview
Audit every committed gauntlet run record against its own persisted evidence and report the
result. This is the gauntlet-proof-audit instance of docs/patterns/audit-loop.md: a skeptic
pass over docs/verification/gauntlet/*/ROUNDS.md (and AB-ROUNDS.md), the eval corpus
/kit:gauntlet produces and lib/gauntlet/stats.sh projects into numbers. Neither of those
checks that a record's CLAIMS match its own EVIDENCE: a "clean=true" that never reconciles with
checker-output.txt, a findings count with no matching finding, a scrubbed key that leaked
anyway, a run-dir that drifted from the contract's naming. This skill never re-runs a probe and
never rewrites a historical record; it reports discrepancies for the operator.
The four slots (per the audit-loop pattern)
| Slot | This instance |
|---|---|
| Item set | git ls-files 'docs/verification/gauntlet/*/ROUNDS.md' 'docs/verification/gauntlet/*/*-ROUNDS.md' 'docs/verification/gauntlet/*/AB-ROUNDS.md' (committed records only; a room copy's own ROUNDS is untracked and never enters the set) |
| Contract | every CLAIM in the record is backed by its committed EVIDENCE: markers well-formed; recorded verdict == committed checker-output.txt; findings count reconciles with the rows; scrub clean (no resolved credential VALUE in committed evidence; a bare op:// pointer is allowed, not a leak); run-dir grammar conforms; a quoted finding string is present in the cited transcript |
| Evidence class | Tier 1: the committed record files themselves via grep/wc/diff. Tier 2: kit:audit-scanner reads a quoted finding against the transcript. Evidence gitignored as a room artifact (transcript pruned) = UNTESTABLE → UNSURE. Transcripts are not in git: unpack the corpus per docs/verification/gauntlet/CORPUS.md before Tier 2 |
| Apply mechanics | REPORT-first: a genuine discrepancy is FLAGGED with a dated correction note appended to the record (never a silent rewrite of the historical claim); UNSURE/DANGER listed in the PR body; REMOVE is disallowed (a record is evidence, not deleted) |
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.
- 2d ago Changed · +3 lines 787148fb9249
- 11d ago Changed · -2 lines a7d1b8290c55
- 1mo ago Changed · -72 tokens per session ebfe791670aa
- 1mo ago Changed · +6 lines be9c5591e086
- 1mo ago First seen · 100 lines · 177 tokens per session scan A 414625fb9ed2
gauntlet-proof-audit is a skill published in the GitHub repository dwarvesf/dwarves-kit (12 stars, last pushed 2d ago), licensed MIT. It adds 105 tokens to every session and 2,130 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 2026-09-04.
Other skills, from other repositories
witness
Independently witness that an Allium loop's convergence claim is true and was reached honestly. Use when the user wants to verify a loop's self-report, confirm tests really pass and no generated test was weakened, produce a convergence certificate or witness record, gate CI on a trustworthy signal, or check that an…
walkthrough
Generate a Phase-2 Walkthrough artifact (walkthrough.md) once implementation and verification are complete. Captures a Change Summary, Verification Steps (commands + unit tests + automated browser testing outcomes), Visual Proof (screenshots/recordings embedded directly in the file), and a Review Gate (final diff + PR…
refactoring-workflow
Improve the structure of existing code without changing its behaviour, in small verified steps under a green test suite. Use when the user asks to refactor, clean up, restructure or simplify code, wants to reduce duplication or coupling, is preparing a codebase for a feature it cannot currently accommodate, or when…
verify-implementation
A coordinator that runs every verification skill registered in a project and combines the results into one report. It also suggests how to fix issues and supports rechecking after approved changes.
refactor
Code refactoring workflow - analyze → plan → implement → review → validate.
verify-against-rubric
Spawn a stateless, independent sub-agent with ONLY the artifact path, the locked rubric and read-only tools, returning a structured per-criterion verdict. Use after pr-package, contract-signoff, or implement-approved-slice on HIGH-complexity slices needing independent verification; not on LOW or MEDIUM slices…