stigmergy: Instructions file for Claude Code

CLAUDE.md

stigmergy CLAUDE.md is an instructions file for Claude Code from sturlese/stigmergy. It costs 1,254 tokens per session, scanned A, original, Apache-2.0.

Project rules for stigmergy, a platform that stores knowledge in Git and Markdown while using Postgres as operational state and a searchable index.

In plain words
What is it for?
Use them when changing architecture, capturing information, updating knowledge files, writing Git changes, or maintaining search and access-control behavior.
Why use it?
They define ownership, data integrity, access-control, and writing rules so changes remain consistent and do not expose restricted information.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

This is sturlese/stigmergy's own configuration. It tells Claude Code how to work on stigmergy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything stigmergy configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sturlese/stigmergy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sturlese/stigmergy/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sturlese/stigmergy

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.

agentmods badge for stigmergy CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sturlese/stigmergy/claude-md/github.svg)](https://agentmods.dev/instructions/sturlese/stigmergy/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sturlese/stigmergy/claude-md"><img src="https://agentmods.dev/badge/instructions/sturlese/stigmergy/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.

agentmods 80×15 button for stigmergy CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sturlese/stigmergy/claude-md"><img src="https://agentmods.dev/badge/instructions/sturlese/stigmergy/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,254 This file is loaded in full into every session.
When invoked 1,254 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01254 $0.01254
Opus 5 $0.00627 $0.00627
Sonnet 5 $0.00251 $0.00251
Haiku 4.5 $0.00125 $0.00125

Measured 8d ago against content hash d8da96afea0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

stigmergy 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 8d 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.

CLAUDE.md · 89 lines

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.

Stigmergy project doctrine

This repository owns the platform. The knowledge repository is a separate Git checkout configured with STIGMERGY_REPO; it owns current Markdown knowledge and its operational control files.

Read the implementation specification at specs/karpathy-team-wiki.md before changing architecture or product behavior. Active documentation lives in docs/ARCHITECTURE.md, docs/OPERATIONS.md, and docs/RESET.md. Code and tests are authoritative when older prose disagrees.

Invariants

  1. Git and Markdown are current knowledge. Postgres is operational state and a rebuildable index.
  2. Every adapter produces the same kind-free CaptureEnvelope before queueing.
  3. Original bytes and readable source pages are immutable during ordinary filing and gardening.
  4. One serialized writer owns every Git mutation and records one commit and one change ledger row.
  5. ACL policy is shared. A write may never expose narrower evidence to broader readers.
  6. The librarian owns notes and concepts. Entity files are minimal machine data owned by entity primitives; raw entity files are not ordinary searchable pages.
  7. No active write state waits for human approval. Supported uncertainty is represented honestly.
  8. Corpus-health findings are preventable or autonomously repairable; they are not human tasks.
  9. Product capabilities are available through Slack, MCP, or the backoffice. Installed CLI commands are service, bootstrap, security, index-operation, or local-bridge entry points.
  10. Every model-backed path is built by kernel.llm from its closed allowlist through the single OpenRouter boundary (spec §4.1). Same-model provider failover is allowed; model fallback and direct Anthropic, OpenAI, or Gemini credentials are not. No new model without updating the allowlist and the specification together.
  11. Comments and docstrings explain only a local non-obvious invariant or mechanism. History and design narration belong in Git and the specification.

Read the full file on GitHub · 89 lines

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.

  1. 8d ago First seen · 89 lines · 1,254 tokens per session scan A d8da96afea0b

Subscribe to this mod's changes

stigmergy CLAUDE.md is an instructions file published in the GitHub repository sturlese/stigmergy (9 stars, last pushed 13d ago), licensed Apache-2.0. It adds 1,254 tokens to every session, about $0.0063 per session on Opus 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.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens