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/pocgit 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/poc)<a href="https://agentmods.dev/commands/solanabr/auditor-skill/poc"><img src="https://agentmods.dev/badge/commands/solanabr/auditor-skill/poc.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 | $0.00088 | $0.01357 |
| Opus 5 | $0.00044 | $0.00678 |
| Sonnet 5 | $0.00018 | $0.00271 |
| Haiku 4.5 | $0.00009 | $0.00136 |
Grade A, and why
auditor:poc 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
auditor-skill — Executable Proof-of-Concept
Arguments: $ARGUMENTS
Turn a confirmed finding into a runnable exploit. Read OUTPUT-RULES.md first (severity 1-10, the Rule 5b gate — the finding must already carry a filled Reachability + Math/State-Bounds block, Attacker-Model for N≥7) and references/orchestration/poc-harness.md (the finding-type → framework matrix and the [PoC-*] evidence tiers this command emits). A PoC is evidence that upgrades an asserted finding to a demonstrated one — it never invents a finding that Rule 5b did not already confirm.
Steps
-
Resolve the finding. Locate the target: a finding id (
F-xxx) resolved from the latestaudit_<n>/REPORT.md, or a rawfile:line. Read its full finding block and its context worksheet underaudit_<n>/worksheets/context/*(the reconstructed instruction/state model the PoC will drive). Pin the audited commit the report names — the harness reproduces that commit, notHEAD. -
Severity gate. By default only High/Critical (N≥7) findings earn an executable PoC — a runnable exploit is the Rule 5b PoC those severities demand, and spending the harness budget on low-severity items is waste.
--forceoverrides the gate for a deliberately-requested lower-severity demonstration. A finding still at[UNCONFIRMED]/[PARTIAL]is not eligible — confirm it through Rule 5b first. -
Detect the toolchain (never assume). Probe what is actually installed:
cargo build-sbf --version(SBF program build),- surfpool MCP reachable (mainnet-fork execution),
trident --version/cargo fuzz --versionon PATH (coverage-guided fuzzing). Record which are present. A missing tool is a blocker to name, not a reason to fabricate.
-
Pick the framework by finding type (matrix in
references/orchestration/poc-harness.md):- logic / access-control / signer / owner / PDA / CPI → Mollusk single-instruction harness (fastest, deterministic, one
process_instruction). - multi-step lifecycle (init → mutate → withdraw, cross-instruction state) → LiteSVM stateful sequence.
- economic / oracle / MEV → Surfpool mainnet-fork (
--fork) — reproduce deposit→manipulate→withdraw against forked pool state for a real P/L figure. - fuzz-discoverable parse / deser / math → Trident / cargo-fuzz (
--fuzz) — emit the fuzz target that finds the crashing input.--fork/--fuzzforce the Surfpool / fuzz path respectively when the finding type is ambiguous.
- logic / access-control / signer / owner / PDA / CPI → Mollusk single-instruction harness (fastest, deterministic, one
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 · 52 lines · 0 tokens per session scan A ae942546fa9a
auditor:poc is a command published in the GitHub repository solanabr/auditor-skill (52 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 1,357 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
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.