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 ccashwell/evm-cortex --skill pashov-audit-pipelinegit clone --depth 1 https://github.com/ccashwell/evm-cortexWrote 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/ccashwell/evm-cortex/pashov-audit-pipeline)<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/pashov-audit-pipeline"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/pashov-audit-pipeline/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/ccashwell/evm-cortex/pashov-audit-pipeline"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/pashov-audit-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 134 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- medium Data Exfiltration · line 15 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00166 | $0.05698 |
| Opus 5.5 | $0.00066 | $0.02279 |
| Sonnet 5.5 | $0.00033 | $0.01140 |
| Haiku 4.5 | $0.00017 | $0.00570 |
Grade A, and why
pashov-audit-pipeline scanned grade A with 1 finding 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 17d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf https://raw.githubusercontent.com/pashov/skills/main/solidity-auditor/VERSION How it starts
The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pashov Audit Pipeline
You are the orchestrator of a parallelized smart contract security audit.
Twelve specialized agents attack the same codebase at once, then their output is deduplicated, gated, and assembled into a single report. Nine work a single lens — arithmetic, permissions, economics, execution flow, invariants, periphery code, first-principles reasoning, asymmetry, and external boundaries. Three are gap-hunters that report only what lives at the seam between lenses, which is precisely the class a single-lens scan structurally cannot see.
Vendored from the Pashov Audit Group's open-source approach (github.com/pashov/skills), skill solidity-auditor, VERSION 4 (see the VERSION file alongside this one). Everything under references/ is upstream content carried over intact, with four documented EVM Cortex deviations:
references/orchestration.mdis upstream'sSKILL.md, vendored verbatim so the turn-by-turn procedure (memory read, prune, bundle build, run files, assembly) stays a file-by-file diff against upstream. Where any reference file says "SKILL.md Turn N", it means that file.references/judging.mdcarries an appended severity/PoC addendum required by this repo's finding-output-format, severity-matrix, and poc-execution rules.on-chain/off-chainare normalized toonchain/offchainacrossreferences/prose and in the one disclaimer stringassemble.shprints, per this repo's style rule.assemble.shcarries a file-level# shellcheck disable=SC2034directive on line 2, because this repo's CI runs ShellCheck at warning level over every.shfile and the assembler'sreadloops bind TSV columns it does not use. Nothing else in the script differs.
Every other EVM Cortex adaptation — agent mapping, context package, Foundry pre-flight, the severity line in each finding block, and the Turn 6 annex — lives in this SKILL.md only, so an upstream re-sync replaces references/ cleanly. Check for a newer upstream revision before a high-stakes audit:
curl -sf https://raw.githubusercontent.com/pashov/skills/main/solidity-auditor/VERSION
If that returns a number greater than 4, this skill is behind upstream.
What ships with it
22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agent-prompts.md 5.5 KB
- references/assemble.sh 17 KB runs code
- references/dedup-and-assembly.md 32 KB
- references/hacking-agents/access-control-agent.md 1.8 KB
- references/hacking-agents/asymmetry-agent.md 4.6 KB
- references/hacking-agents/boundary-agent.md 6.3 KB
- references/hacking-agents/economic-security-agent.md 2.5 KB
- references/hacking-agents/execution-trace-agent.md 2.7 KB
- references/hacking-agents/first-principles-agent.md 2.0 KB
- references/hacking-agents/flow-gap-agent.md 5.7 KB
- references/hacking-agents/invariant-agent.md 4.3 KB
- references/hacking-agents/math-precision-agent.md 3.8 KB
- references/hacking-agents/numerical-gap-agent.md 5.1 KB
- references/hacking-agents/periphery-agent.md 3.3 KB
- references/hacking-agents/shared-rules.md 5.8 KB
- references/hacking-agents/trust-gap-agent.md 3.9 KB
- references/judging.md 7.9 KB
- references/orchestration.md 41 KB
- references/report-formatting.md 19 KB
- references/report-language.md 7.2 KB
- references/senior-auditor-sop.md 4.0 KB
- VERSION 2 B
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.
- 17d ago Changed · -22 lines · +64 tokens per session scan B → A a67083f84593
- 1mo ago First seen · 289 lines · 102 tokens per session scan B a333399785b8
pashov-audit-pipeline is a skill published in the GitHub repository ccashwell/evm-cortex (131 stars, last pushed 17d ago), licensed MIT. It adds 166 tokens to every session and 5,698 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.
marginfi
MarginFi — Solana lending and borrowing.
devtools-event-client
Create typed EventClient for a library. Define event maps with typed payloads, pluginId auto-prepend namespacing, emit()/on()/onAll()/onAllPluginEvents() API. Connection lifecycle (5 retries, 300ms), event queuing, enabled/disabled state, SSR fallbacks, singleton pattern. Unique pluginId requirement to avoid event…