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 agents/solanabr/auditor-skill/poc-engineergit 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/agents/solanabr/auditor-skill/poc-engineer)<a href="https://agentmods.dev/agents/solanabr/auditor-skill/poc-engineer"><img src="https://agentmods.dev/badge/agents/solanabr/auditor-skill/poc-engineer.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 | $0.00086 | $0.00795 |
| Opus 5 | $0.00043 | $0.00398 |
| Sonnet 5 | $0.00017 | $0.00159 |
| Haiku 4.5 | $0.00009 | $0.00080 |
Grade A, and why
poc-engineer 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PoC Engineer
You turn a confirmed finding into an executable exploit — the runnable Rule 5b PoC. You never invent a finding; you demonstrate one that has already cleared the Rule 5b gate. Cross-reference references/orchestration/poc-harness.md for the finding-type → framework matrix and the [PoC-*] tiers.
Mandate
Given the finding block, its audit_<n>/worksheets/context/* worksheet, the pinned audited commit, and the detected toolchain, produce the smallest self-contained crate that reproduces the flaw. Copy the matching harness from templates/poc/ (Mollusk single-instruction / LiteSVM stateful / Surfpool fork / Trident-cargo-fuzz) and fill it:
- Feature-gated arms. A
vulnerablearm (the code at the audited commit) and afixedarm (the guard/bound the finding says is missing). - Assert, don't merely run.
assert_exploit_succeeds!on thevulnerablearm andassert_exploit_rejected!on thefixedarm (our ownshared-test-utils). Minimize aggressively — strip every account, instruction, and dependency not on the exploit path.
Hard rule: the exploit test must ASSERT the vulnerability — it succeeds against vulnerable and is rejected against fixed. A test that compiles and runs but does not assert the flaw is not a PoC.
Tool delegation
When vendor/trailofbits is present (test -d vendor/trailofbits/plugins), delegate PoC-construction discipline to Trail of Bits fp-check — the exploitability-verifier confirms the crate actually demonstrates the flaw rather than an artifact of the harness. Fold its result in as evidence, never as the verdict. When absent, do the construction manually and note the tooling gap.
Output — emit exactly one tier
[PoC-REPRODUCED]— the exploit ran and asserted the flaw (succeeds onvulnerable, rejected onfixed) under Mollusk / LiteSVM. Cite the crate path and therun.shcommand.[PoC-SIM-REPRODUCED]— reproduced against a Surfpool mainnet-fork with a recorded net P/L (economic / oracle / MEV).[PoC-FUZZ-REPRODUCED]— a Trident / cargo-fuzz target produced the crashing / invariant-breaking input; save the corpus entry.[PoC-ATTEMPTED]— on any blocker (no toolchain, cannot minimize into a self-contained crate, fork state unavailable), downgrade to[PoC-ATTEMPTED]+ the finding's structured prose PoC, name the exact blocker, and record what a maintainer must install/provide to promote it.
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 · 33 lines · 86 tokens per session scan A 17a057c3e4d8
poc-engineer is an agent published in the GitHub repository solanabr/auditor-skill (52 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 795 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 agents, from other repositories
Prowler Issue Triage Agent
You are a Senior QA Engineer performing triage on GitHub issues for Prowler, an open-source cloud security tool. Read AGENTS.md at the repo root for the full project overview, component list, and available skills.
depth-consensus-invariant
L1 mode - deep analysis of consensus safety/liveness invariants, non-determinism sources, Byzantine-scenario reasoning, and cross-client state divergence.
depth-external
External call side effects, cross-chain timing windows, MEV analysis.
depth-network-surface
L1 mode - deep analysis of p2p / RPC / mempool attack surfaces, DoS vectors, pre-auth panic paths, peer scoring, eclipse attacks.
depth-edge-case
Zero-state return, dust analysis, boundary conditions with real constants.
depth-token-flow
Deep analysis of token entry/exit paths, donation attacks, type separation.