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 agentmods add instructions/lucabiz/agentscribe/claude-mdgit clone --depth 1 https://github.com/Lucabiz/agentscribeWrote 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/lucabiz/agentscribe/claude-md)<a href="https://agentmods.dev/instructions/lucabiz/agentscribe/claude-md"><img src="https://agentmods.dev/badge/instructions/lucabiz/agentscribe/claude-md.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 | $0.00601 | $0.00601 |
| Opus 5 | $0.00300 | $0.00300 |
| Sonnet 5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
agentscribe 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 5d 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.
This is a copy
100% identical to agentscribe copilot-instructions.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentscribe
Guidance for AI coding agents working in this repository. This file is the single source of truth. The tool-specific files (
CLAUDE.md,.cursor/rules/,.github/copilot-instructions.md) are generated from it byagentscribe sync— never edit them by hand.
Overview
agentscribe is a small CLI + library that generates tool-specific AI instruction
files (CLAUDE.md, Cursor rules, Copilot instructions, ...) from a single
AGENTS.md, and validates that source. The code lives under src/agentscribe/:
config.py— load configuration fromagentscribe.tomlor[tool.agentscribe].source.py— parse the source and applyagentscribe:only/except/ignorescoping.targets.py— the registry of output files and how each is formatted.sync.py— plan, write, and drift-check target files.lint.py— conservative static checks over the source.detect.py/templates.py— poweragentscribe init.cli.py— argparse front end.
Setup & commands
| Task | Command |
|---|---|
| Install (editable, with dev deps) | pip install -e ".[dev]" |
| Run tests | pytest |
| Lint | ruff check . |
| Format | ruff format . |
| Run the tool | agentscribe <command> (e.g. agentscribe sync) |
Code style & conventions
- Target Python 3.9+. Every module starts with
from __future__ import annotationsso built-in generics (list[str]) are safe in annotations. - Keep runtime dependencies at zero (the only exception is the
tomlibackport on Python < 3.11). Do not add dependencies without strong justification. - Match the surrounding style; keep functions small and pure where possible.
- Generated output must stay deterministic: LF line endings, stable ordering.
Testing
- Run the full suite with
pytestbefore considering a change done. - Add or update tests in
tests/for any behavior you change. - Every CLI command and lint rule should have coverage.
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.
- 5d ago First seen · 56 lines · 601 tokens per session scan A 7a0180084ee6
agentscribe CLAUDE.md is an instructions file published in the GitHub repository Lucabiz/agentscribe (3 stars, last pushed 26d ago), licensed MIT. It adds 601 tokens to every session, about $0.0030 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agentscribe copilot-instructions.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
aidevops AGENTS.md
AGENTS.md instructions for marcusquinn/aidevops, covering ai devops framework - developer guide, quick reference, two agents.md files, development lifecycle and contributing.
aidevops codacy.instructions.md
Configuration for AI behavior when interacting with Codacy's MCP Server.
aidevops CLAUDE.md
Claude Code instructions for marcusquinn/aidevops: See AGENTS.md for the authoritative AI assistant guidance.
agents-reverse-engineer AGENTS.md
Instructions for GeoloeG-IsT/agents-reverse-engineer, covering agents-reverse-engineer, stack, subdirectories, architecture and behavioral contracts.
project-starter-template-es-ai AGENTS.md
AGENTS.md instructions for brayandiazc/project-starter-template-es-ai, covering agents.md — [nombredelproyecto], resumen del proyecto, mapa del repositorio (lee esto primero), configuración y comandos and acuerdo de trabajo.
agent-operating-protocol AGENTS.md
Instructions for ryu-tada/agent-operating-protocol, covering agents.md - agent operating protocol, 0. instruction priority and trust boundaries, 1. core operating stance, 2. why high-agency agents feel strong and 3. default work loop.