Borrowing it
Nothing to install: this file belongs to artvepa80/Agents-Hefesto. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/artvepa80/Agents-Hefesto/main/CLAUDE.mdgit clone --depth 1 https://github.com/artvepa80/Agents-HefestoWrote 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/instructions/artvepa80/agents-hefesto/claude-md)<a href="https://agentmods.dev/instructions/artvepa80/agents-hefesto/claude-md"><img src="https://agentmods.dev/badge/instructions/artvepa80/agents-hefesto/claude-md/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/instructions/artvepa80/agents-hefesto/claude-md"><img src="https://agentmods.dev/badge/instructions/artvepa80/agents-hefesto/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.06789 | $0.06789 |
| Opus 5.5 | $0.02716 | $0.02716 |
| Sonnet 5.5 | $0.01358 | $0.01358 |
| Haiku 4.5 | $0.00679 | $0.00679 |
Grade A, and why
Agents-Hefesto CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 551 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HefestoAI — release truth engine for AI-generated code — Claude Code Guidelines
Enterprise Code Quality & Security Development Standards
0. Agent Procedural Workflow (MANDATORY)
Session Start Checklist
On start of ANY task or session, the agent MUST read these files in order:
CLAUDE.md(this file — project rules and standards)docs/CLAUDE_HEFESTO.md(Hefesto-specific development guidelines and architecture)MEMORY.md(project status, pending blockers, credentials context)CHANGELOG.md(recent changes, current version)README.md(public-facing docs, version badge, feature table)task.mdandwalkthrough.md(if present — task-specific context)
Internal work logs and handoffs are kept outside this public repository; do not add them here (the guard rejects docs/worklog/).
Do NOT skip this step. Do NOT guess project state from memory.
Socratic-Adaptive Method (MSA)
Principle: Before acting, understand. Before proposing, diagnose.
Phase 1 — Diagnosis (always)
- Read the relevant code before proposing changes.
- Ask yourself: "What already exists that solves this partially or fully?"
- Document findings with concrete file paths and line numbers.
- If evidence contradicts the task, report it before proceeding.
Phase 2 — Decision (max 2 questions to user)
- Ask only if truly blocking (ambiguity, destructive action, 2+ valid approaches).
- If not blocking, proceed with explicit safe assumptions: "Assuming X (safe default). Proceeding."
- Never ask what you can resolve by reading the repo.
Phase 3 — Execution (minimal diffs)
- Reuse what exists before creating new modules.
- Every change must have evidence: "Changed X because Y (found in
file:line)." - If a plan requires >3 new files, question whether it can be done with fewer.
Phase 4 — Verification (mandatory)
- Run repo verifiers before declaring complete.
- Compare expected result vs actual result.
- If something fails, diagnose (Phase 1) before retrying.
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 Changed · -3 lines · +7 tokens per session 9268be84a526
- yesterday Changed · +3 lines · +489 tokens per session 4f59322f1628
- 2d ago Changed · +2 lines · +119 tokens per session d8f59107e1ca
- 3d ago Changed ad344a8c0b99
- 7d ago Changed · +11 lines · +187 tokens per session cb87f01ed330
- 8d ago Changed · +8 lines · +144 tokens per session dd825fedcbd7
- 9d ago Changed · +17 lines · +398 tokens per session 8574eb36bdc6
- 10d ago Changed · +2 lines · +101 tokens per session 203b95942662
- 11d ago Changed · +8 lines · +278 tokens per session 5d5aa89f53c0
- 12d ago First seen · 503 lines · 5,066 tokens per session scan A 044d18a3df0f
Agents-Hefesto CLAUDE.md is an instructions file published in the GitHub repository artvepa80/Agents-Hefesto (7 stars, last pushed today), licensed MIT. It adds 6,789 tokens to every session, about $0.0272 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.