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/geograms/geogram/claude-mdgit clone --depth 1 https://github.com/geograms/geogramWhat 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 | $0.00658 | $0.00658 |
| Opus 5 | $0.00329 | $0.00329 |
| Sonnet 5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
geogram 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 2d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory
Key Decisions
-
DO NOT DUPLICATE CODE FUNCTIONALITY. Write libraries and make sure that apps are mostly using a single file without duplication of functionality in other parts of the code
-
When writing code for a station server, there are two implementations so write code that uses a library or common method that is called by the two implementations.
-
Always use ProfileStorage methods (not raw File/Directory) when accessing files inside the {callsign} profile folder — the folder may be inside an encrypted SQLite storage. Use AppService().profileStorage to get the storage instance.
-
Station code reuse: Never implement feature code on either CLI or Desktop station directly. Always write to shared libraries/mixins (lib/server/mixins/) and have both stations use the same code.
There is a script ./launch-desktop.sh to launch the client on this laptop and ./server-deploy.sh when needed to upload/update the server station.
Always use ./launch-desktop.sh for testing the code and client implementations, don't launch it separately without that script
Read ./docs/API.md for the debug API that automates testing. When a debug API endpoint does not exist, create one.
Never implement code features without testing them yourself first. Do the deployment, test that it works as intended.
Use ./docs/reusable.md to reuse code instead of duplicating functionalities, document new reusable components there
Always commit your changes with a proper change log
Write code that is based on DART and can run from the command line for libraries, so we can reuse it in other platforms
Another claude instance might be running on the same code base, be carefull. When you find code that is breaking your compilation to unrelated changes then ask the human
Release Process
- Bump version in
pubspec.yaml - Commit (pre-commit hook auto-updates
lib/version.dartviatool/update_version.dart) - Tag with
git tag v<version>and push withgit push --tags - Create GitHub release — CI workflows will
sedpubspec.yaml from the tag and regenerateversion.dartbefore building
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.
- 2d ago First seen · 45 lines · 658 tokens per session scan A c53f5fc3588e
geogram CLAUDE.md is an instructions file published in the GitHub repository geograms/geogram (24 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 658 tokens to every session, about $0.0033 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 2026-08-30.
Other instructions, from other repositories
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.
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.
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).
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.