Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/woohyun212/security-skillnpx agentmods add skills/woohyun212/security-skill/spec-to-code-complianceWrote 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/woohyun212/security-skill/spec-to-code-compliance)<a href="https://agentmods.dev/skills/woohyun212/security-skill/spec-to-code-compliance"><img src="https://agentmods.dev/badge/skills/woohyun212/security-skill/spec-to-code-compliance.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 | $0.00019 | $0.02615 |
| Opus 5 | $0.00010 | $0.01307 |
| Sonnet 5 | $0.00004 | $0.00523 |
| Haiku 4.5 | $0.00002 | $0.00262 |
Grade A, and why
spec-to-code-compliance 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What this skill does
Verifies that a code implementation faithfully matches its specification or design document. Parses the spec into discrete requirements, maps each requirement to the corresponding code location, and flags deviations — missing controls, incorrect state transitions, wrong error handling, overlooked edge cases — with severity ratings and MITRE ATT&CK technique mappings where applicable. Produces a compliance matrix as the primary output.
Applicable to:
- Smart contracts: EIP compliance (ERC-20, ERC-721, ERC-4626)
- API implementations: OpenAPI / Swagger spec adherence
- Protocol implementations: RFC compliance (TLS, OAuth 2.0, JWT)
- Security policies: access control matrices, data handling policies
This skill is distinct from threat-model, which identifies risks before implementation. Here the implementation already exists and is evaluated against a written specification.
When to use
- After implementing a feature whose specification makes explicit security guarantees (e.g., "only owner can withdraw")
- When auditing a smart contract against its EIP or whitepaper
- When reviewing an RFC-defined protocol implementation for compliance gaps
- When a security policy document exists and code must demonstrably enforce it
- During pre-audit preparation to surface compliance gaps before an external reviewer does
- When a spec has been updated and existing code needs re-validation
Prerequisites
- A written specification document (RFC, design doc, EIP, OpenAPI schema, security policy)
- Access to the codebase under review (source files readable)
- (Optional)
mitre-attack-lookupskill available for ATT&CK technique mapping
Inputs
| Item | Description | Example |
|---|---|---|
SPEC_SOURCE |
Specification document or URL | docs/eip-4626.md, https://www.rfc-editor.org/rfc/rfc7519 |
SPEC_TYPE |
Kind of specification | EIP / RFC / OpenAPI / design-doc / policy |
CODEBASE_PATH |
Root path of the implementation | ./contracts/, ./src/ |
LANGUAGE |
Primary implementation language | Solidity, Python, Go, TypeScript |
REVIEW_SCOPE |
Optional: limit to specific modules or sections | Auth flow only, Section 4.1–4.6 of RFC |
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 · 214 lines · 19 tokens per session scan A 5757cf965d3b
spec-to-code-compliance is a skill published in the GitHub repository woohyun212/security-skill (21 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 2,615 once invoked, about $0.0001 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…