What is hefesto-dogfood?

A repository rule that requires changed code and configuration files to be checked with HefestoAI, a code-analysis tool, before work is finished. High- and critical-severity findings must be fixed or explained in the pull request.

Use it as a code-change and pull-request checklist: find changed files, run HefestoAI, fix serious findings, and document the command and result under a Dogfood heading.

It adds a repeatable check for problems in every change and records the results for reviewers. It also provides a local command when the hosted check cannot be used.

hefesto-dogfood — Cursor rule for Cursor 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.

Clone the repo

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

Made for: Cursor.

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/rules/artvepa80/agents-hefesto/hefesto-dogfood/github.svg)](https://agentmods.dev/rules/artvepa80/agents-hefesto/hefesto-dogfood)

Your own site

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

Per session 393 This file is loaded in full into every session.

When invoked 393 The same file — it is already loaded in full.

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	$0.00393	$0.00393
Opus 5.5	$0.00157	$0.00157
Sonnet 5.5	$0.00079	$0.00079
Haiku 4.5	$0.00039	$0.00039

Measured today against content hash c62c26dfaf9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hefesto-dogfood 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 today.

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.

.cursor/rules/hefesto-dogfood.mdc · 30 lines

What it actually says

Dogfood HefestoAI on your changes

After you create or edit code or config in this repo, analyze every changed file with HefestoAI before you finish.

List the changed files: git diff --name-only origin/main...HEAD plus uncommitted changes (git status --porcelain).
Analyze them:
- 5 files or fewer: call the hefestoai MCP server's analyze tool once, with files: [{"path": "<relative/posix/path>", "content": "<file text>"}] (up to 20 files, 100 KB each; no .., absolute paths, .git or .hefesto.yaml). Optional: severity (LOW..CRITICAL), format (json or sarif).
- More than 5 files, or the MCP tool is unavailable or rate-limited: the hosted MCP allows 10 calls per minute, so use the local CLI instead: HEFESTO_TELEMETRY=0 hefesto analyze <files>. If hefesto is not on PATH, run HEFESTO_TELEMETRY=0 python -m hefesto analyze <files> (install with pip install hefesto-ai if needed).
Fix every HIGH or CRITICAL finding. If one is a false positive, say why in one line.
Put the result in the PR body under a Dogfood heading: the exact tool call or command and its output (or a finding count summary when long), plus the fixes or false-positive explanations.

Files the analyzer does not support are fine to skip; list them as skipped.

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.

today First seen · 30 lines · 393 tokens per session scan A c62c26dfaf9f

Subscribe to this mod's changes

hefesto-dogfood is a cursor rule published in the GitHub repository artvepa80/Agents-Hefesto (7 stars, last pushed today), licensed MIT. It adds 393 tokens to every session, about $0.0016 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 2026-10-17.

Code review Security ai-code cli code-quality developer-tools github-actions

hefesto-dogfood

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Dogfood HefestoAI on your changes

What this file has done since we first saw it

Other cursor rules, from other repositories

archguardian

check

hatch3r-anti-duplication

cli-audit-code

baseline

scan