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.
git 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-assist)<a href="https://agentmods.dev/commands/solanabr/auditor-skill/audit-assist"><img src="https://agentmods.dev/badge/commands/solanabr/auditor-skill/audit-assist.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 5.1 | $0.00076 | $0.01239 |
| Opus 5 | $0.00038 | $0.00620 |
| Sonnet 5 | $0.00015 | $0.00248 |
| Haiku 4.5 | $0.00008 | $0.00124 |
Grade A, and why
auditor:audit-assist 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 8d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
auditor-skill — Flow B: AI-Assisted Iterative Audit (Human-in-the-Loop)
Arguments: $ARGUMENTS
Run the same lifecycle as /auditor:audit-cycle, but stop at checkpoints and let the human steer. Read OUTPUT-RULES.md first (format, severity 1-10, Rule 5b gate) and references/audit-lifecycle/methodology.md (the firm-spine → skill-mechanism mapping). This is the collaborative mode: the agent does the mechanical review; the human resolves the judgment calls a tool cannot (business intent, trust boundaries, severity of a business-logic gap). Think ToB weekly progress report + Zellic client discussion.
Checkpoint protocol
At every checkpoint, surface a compact status and then wait for the human before proceeding:
- (a) Confirmed findings so far — severity-ordered, each already through Rule 5b +
references/false-positives.md. - (b) Next-focus plan — which surfaces / instructions / vectors are queued next and why.
- (c) Targeted questions — the specific things only the human can answer: business context, the intended trust / threat model, whether a flagged behavior is intentional, and severity calls that depend on off-chain assumptions. Ask sharp, answerable questions — not "anything to add?".
Fold the human's answers back in, re-synthesize, and continue.
Lifecycle with checkpoints
-
Scope / intake. Discover the repo, declare scope (Rule 0), pin the commit. ⏸ Checkpoint 1 — after scope: confirm the scope boundary, the pinned commit, and any
QUESTIONS.mdanswers the human wants to override before a single file is judged. Persist the confirmed answers toaudit_<n>/intake.md(/intake) so both flows and the report read one source of truth. -
Context reconstruction (Phase 0.5). Spawn
context-builder; it writes worksheets toaudit_<n>/worksheets/context/. ⏸ Checkpoint 2 — after context: present the instruction matrix + state model and the reconstructed invariants/assumptions. Ask the human to correct anyUNKNOWN — needs manual reviewitems and confirm the trust model. Their corrections seed every later phase. With the trust model confirmed, buildaudit_<n>/threat-model.md(/threat-model) — asset inventory + actor×capability + trust boundaries — which feeds report §4.4/§4.6/§4.7 and the review's attacker goals.
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.
- 8d ago First seen · 42 lines · 76 tokens per session scan A 01dd30b59681
auditor:audit-assist is a command published in the GitHub repository solanabr/auditor-skill (53 stars, last pushed 5d ago), licensed MIT. It adds 76 tokens to every session and 1,239 once invoked, about $0.0004 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
audit-solana
Security audit for Solana programs (Anchor/native).
build-unity
Build Unity project (WebGL, Desktop, or PSG1).
plan-feature
Plan feature implementation with technical specifications for Solana projects.
deploy
Deploy Solana program (devnet first, then mainnet).
generate-idl-client
Generate TypeScript client from Solana program IDL using Codama or Anchor.
profile-cu
Profile compute unit usage per instruction in a Solana program.