A pre-commit and continuous-integration quality check for AI-generated code. HefestoAI looks for semantic drift, security problems, and reliability issues before code is committed.

Use it to analyse a repository or changed files, enforce a pre-commit check, and require problems to be fixed or reviewed before committing.

It catches certain problems in generated code before they reach a commit or build pipeline. It can also stop a commit when findings exceed the configured threshold.

hefestoai — Skill for Claude Code by artvepa80/Agents-Hefesto

Install

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.

Any agent

npx skills add artvepa80/Agents-Hefesto --skill hefestoai

Clone the repo

git clone --depth 1 https://github.com/artvepa80/Agents-Hefesto

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/artvepa80/agents-hefesto/hefestoai/github.svg)](https://agentmods.dev/skills/artvepa80/agents-hefesto/hefestoai)

Your own site

<a href="https://agentmods.dev/skills/artvepa80/agents-hefesto/hefestoai"><img src="https://agentmods.dev/badge/skills/artvepa80/agents-hefesto/hefestoai/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/artvepa80/agents-hefesto/hefestoai"><img src="https://agentmods.dev/badge/skills/artvepa80/agents-hefesto/hefestoai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,044 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00061	$0.01044
Opus 5.5	$0.00024	$0.00418
Sonnet 5.5	$0.00012	$0.00209
Haiku 4.5	$0.00006	$0.00104

Measured yesterday against content hash b2763600f0bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hefestoai 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 yesterday.

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.

skills/hefestoai/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HefestoAI — verify before commit

HefestoAI (hefesto-ai on PyPI) is an independent quality gate for AI-generated code.

Package: hefesto-ai (PyPI) | Version: 4.20.3 | License: MIT | Python >= 3.10

Required workflow (do this before commit)

Ensure the tool is installed: pip install hefesto-ai (or confirm hefesto is on PATH).
Analyze the repo or changed paths:
```
hefesto analyze . --fail-on HIGH
```
If exit code is not 0, fix the reported issues (or ask the user) before committing.
Prefer a hook for every commit: add the hefesto-analyze pre-commit hook to the project's .pre-commit-config.yaml (it checks Python files only), then run pre-commit install:
```
repos:
  - repo: https://github.com/artvepa80/Agents-Hefesto
    rev: v4.20.3
    hooks:
      - id: hefesto-analyze
```
Without the pre-commit framework: hefesto install-hooks (from 4.17.1) installs a git pre-commit hook that analyzes the staged files (their working-tree copy) with the Python that installed it; it exits 1 if it installed nothing or core.hooksPath is set.

Exit codes: 0 clean · 1 gate failure / error · 2 drift threshold.

When this skill applies

User asks to commit, open a PR, or “ship” after AI edits
User mentions HefestoAI, semantic drift, pre-commit quality, or AI code review
Integrating with Claude Code, Cursor, Codex, or CI

Progressive docs (load only what you need)

File	Contents
commands.md	CLI flags, workflows, exit codes
issue_types.md	Issue catalog and severities
semantic_drift.md	Semantic drift detection
reliability_drift.md	RELIABILITY_* rules
integration.md	Hooks, CI/CD, MCP
analysis/SKILL.md	Interpret analyze output

Architecture (short)

Phase 0 — static (always): complexity, smells, security, best practices, resource safety; plus the DevOps and cloud analyzers hefesto analyze runs (YAML, Shell, Dockerfile, Terraform, SQL, COBOL, PowerShell, JSON, TOML, Makefile, Groovy, CloudFormation, ARM, Helm, Serverless).

Read the full file on GitHub · 85 lines

Files

What ships with it

11 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.

Changes

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.

yesterday First seen · 85 lines · 61 tokens per session scan A b2763600f0bf

Subscribe to this mod's changes

hefestoai is a skill published in the GitHub repository artvepa80/Agents-Hefesto (7 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 1,044 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-25.

DevOps and cloud Security Testing ai-code cli code-quality developer-tools github-actions

github-actions

Use when authoring or fixing GitHub Actions CI/CD — workflows under .github/workflows, triggers, job matrix, caching, token permissions, OIDC cloud deploys, environment gates, reusable workflows. NOT the Dockerfile or image build strategy (that is docker), NOT the branching model (that is git-workflow), NOT release…

ericrisco/rsc-harness · 81 tokens

argot-check

Score your working changes with argot — flag code foreign to this repo's own patterns (unfamiliar dependencies, APIs, constructs), functions the repo already has, code filed in the wrong place, imports that break the repo's layering, and tests weakened, disabled, or deleted alongside a production change — before…

get-tmonier/argot · 110 tokens

verifier

Use this skill when verifying that a completed Taniwha implementation or composition satisfies its contract's acceptance criteria. The verifier reads the contract, the implementation's source files, and the project context, then writes its own tests against the contract's acceptance criteria, runs them, and reports…

taniwhaai/arai · 122 tokens

hefestoai