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 agentmods add commands/solanabr/auditor-skill/audit-cyclegit clone --depth 1 https://github.com/solanabr/auditor-skillWrote 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/commands/solanabr/auditor-skill/audit-cycle)<a href="https://agentmods.dev/commands/solanabr/auditor-skill/audit-cycle"><img src="https://agentmods.dev/badge/commands/solanabr/auditor-skill/audit-cycle.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.01999 |
| Opus 5 | $0.00034 | $0.01000 |
| Sonnet 5 | $0.00013 | $0.00400 |
| Haiku 4.5 | $0.00007 | $0.00200 |
Grade A, and why
auditor:audit-cycle 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
auditor-skill — Flow A: Automated Audit Cycle → Client Report
Arguments: $ARGUMENTS
Run the full audit-firm lifecycle autonomously, from intake to a deliverable report. Read OUTPUT-RULES.md first (mandatory format, severity 1-10, the Rule 5b validation gate) and references/audit-lifecycle/methodology.md (the firm-spine → skill-mechanism mapping this flow follows). Do not pause for a human — where a firm would ask the client, use the QUESTIONS.md defaults and record the assumption in the report.
Lifecycle
-
Scope / intake (Rule 0 + commit-pin). Discover the repo, declare scope (
SKILL.md→ SCOPE-GATED LOADING), and honor--scope. Pin the audited commit (git rev-parse HEAD) so the report names exactly what was reviewed. If no human is present to answer intake, applyQUESTIONS.mddefaults and list every assumed answer under "Scope & Assumptions". Persist the intake asaudit_<n>/intake.md(the/intakeartifact) so every later phase and the report read one source of truth. -
Context reconstruction (Phase 0.5). Spawn
context-builder(sonnet). It produces the instruction matrix, state model, and per-function worksheets inaudit_<n>/worksheets/context/. No verdicts yet — understanding only. These worksheets are the shared substrate every later phase reuses (avoids re-reconstruction cost).
2b. Threat model. Spawn threat-modeler (opus) → audit_<n>/threat-model.md: asset inventory, an actor×capability table (what each actor must NOT be able to do), and the trust boundaries, built from the context worksheets + intake.md. This seeds report §4.4/§4.6/§4.7 and hands the reviewers concrete attacker goals to test — not verdicts.
- Tool-assisted first pass (tools up-front). If
vendor/trailofbits/pluginsis present (test -d vendor/trailofbits/plugins), run ToBstatic-analysis(SAST) over the in-scope languages and fold the SARIF as evidence that clears the mechanical surface and directs manual attention — not as verdicts (references/orchestration/boundary-map.md). This follows Trail of Bits' precedent of running the toolset (Clippy pedantic,cargo-audit,cargo-outdated) at engagement start so linter/advisory noise is dispatched before the deep human read. If absent, run thediscovery/grep-commands.mdnative scanners and note the tooling gap. Load in-scopereferences/methodologies/*per their protocol markers (SKILL.mdreference table) so domain review has the right playbook.
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 · 47 lines · 67 tokens per session scan A 2f79d66efc4e
auditor:audit-cycle is a command published in the GitHub repository solanabr/auditor-skill (52 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,999 once invoked, about $0.0003 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 2026-08-30.
Other commands, from other repositories
review
Review code changes for Shannon-specific patterns, security, and common mistakes.
debug
Systematically debug errors using context analysis and structured recovery.
pr
Create a PR to main branch using conventional commit style for the title.
audit
Full project audit with Health Score, findings, and a prioritized fix plan.
build-unity
Build Unity project (WebGL, Desktop, or PSG1).
test-ts
Run TypeScript tests for Solana frontends and Anchor programs.