Borrowing it
Nothing to install: this file belongs to NicolasPrimeau/artel. 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/NicolasPrimeau/artel/master/CLAUDE.mdgit clone --depth 1 https://github.com/NicolasPrimeau/artelWrote 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/nicolasprimeau/artel/claude-md)<a href="https://agentmods.dev/instructions/nicolasprimeau/artel/claude-md"><img src="https://agentmods.dev/badge/instructions/nicolasprimeau/artel/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/nicolasprimeau/artel/claude-md"><img src="https://agentmods.dev/badge/instructions/nicolasprimeau/artel/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 | $0.00856 | $0.00856 |
| Opus 5.5 | $0.00342 | $0.00342 |
| Sonnet 5.5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
artel 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 18d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Artel
A self-hosted shared notepad for AI agent fleets: memory that hooks write and recall without the agent asking, curated by an async archivist, meshed across machines.
What It Is
Artel is the memory substrate under a fleet of AI agents. Hooks capture each session into notes and inject the relevant one back, so an agent never has to call it deliberately. An async archivist merges, decays and promotes the notes so the pad improves with use. Any agent that can make HTTP calls can participate: Claude Code, AutoGen, raw API scripts. The harness owns visible coordination; Artel does not compete with it.
Stack
- Python 3.11+ (CI tests 3.11/3.12/3.13), FastAPI, SQLite (WAL mode), sqlite-vec (embeddings)
- MCP adapter on top of core REST API
- Self-hosted, accessible from all machines
Layout
artel/
server/ — FastAPI app, routes, auth
store/ — SQLite models, migrations
archivist/ — async synthesis agent
mcp/ — MCP adapter over REST
scripts/
migration/ — DB migrations
docs/
plan.md — execution plan
spec.md — protocol and data model spec
architecture.md — system design
.claude/
memory/ — agent memory
skills/ — project skills
Core Primitives
- Memory: shared knowledge store with embeddings, confidence scores, provenance
- Procedures (blueprints): a skill compiled into steps the server verifies and hooks surface
- Decisions: append-only record of what was chosen and why
- Events: pub/sub stream
Tasks and messages still exist in the API. Tasks are the rows behind procedure steps;
the agent-operated board (claim, complete, inbox) is not being built on, and
MCP_BOARD_TOOLS=false hides it.
Injection rules
Everything a hook injects is a nudge. Silence is the normal outcome, one line is the
normal maximum, and every hook has a size budget enforced by
tests/test_hook_injection_budget.py. Judge a recall change by its noise rate on the
no-answer prompts in bench/recall, not only by positives served.
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.
- 18d ago Changed · +11 lines · +119 tokens per session 74599c9ab369
- 1mo ago First seen · 78 lines · 737 tokens per session scan A a660702ced73
artel CLAUDE.md is an instructions file published in the GitHub repository NicolasPrimeau/artel (9 stars, last pushed 7d ago), licensed MIT. It adds 856 tokens to every session, about $0.0034 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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.