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/agents-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 | $0.01266 | $0.01266 |
| Opus 5 | $0.00633 | $0.00633 |
| Sonnet 5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
geogram AGENTS.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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
lib/holds the Flutter application code and shared UI/business logic.bin/contains CLI utilities and standalone Dart test runners such asstation_api_test.dart.tests/includes integration-style Dart tests and shell scripts for multi-device scenarios.- Platform targets live in
android/,ios/,linux/,macos/,windows/, andweb/. - Assets and data live in
assets/,languages/,themes/,tiles/, andgames/. - Build and operational scripts are in the repo root and
scripts/.
Core Workflow
- Run the relevant compiler or analyzer after code changes so the edited code is validated.
- Do not claim a feature works until you have verified it yourself.
- Use the debug API in
docs/API.mdfor feature verification whenever possible. - If the required debug API endpoint does not exist, add it, use it to test the feature, and document it in
docs/API.md. - For desktop and general client verification, always launch through
./launch-desktop.sh. - For Android-specific verification, use
./launch-android.sh. - For server-side deployment or validation, use
./server-deploy.sh. - Plan and verify end-to-end behavior yourself instead of waiting for the user to list every validation step.
- Commit your changes after each task with a descriptive sentence-case message.
- Mention bug or ticket identifiers in commit messages when the task is tied to a specific issue.
- Never run
git push,gh release, or other publish steps unless the user explicitly asks. - Never auto-close bug tickets or issues after fixing them; wait for explicit confirmation.
Architecture Constraints
- When accessing anything inside the
{callsign}profile folder, always useProfileStoragemethods rather than rawFileorDirectory. - Obtain profile storage through
AppService().profileStorage. - This rule is mandatory because profile data may live in
EncryptedProfileStoragebacked by SQLite rather than the plain filesystem. - Do not implement station features separately in CLI and Desktop station classes.
- Put shared station logic in reusable libraries or mixins, especially under
lib/server/mixins/, and have both station implementations use the same code. - The two station entry points are
lib/cli/pure_station.dartandlib/station.dart; keep behavior aligned through shared code. EmailHandlerMixinis the shared email implementation for both station types; extend shared behavior there instead of duplicating email logic.- The offline ECIES email cache path is intentionally disabled at the moment; reconnect delivery still relies on the pending-email path until encryption is redesigned.
- Prefer Dart libraries that can run from the command line so logic can be reused across platforms.
- Reuse existing components instead of duplicating them, and document new reusable building blocks in
docs/reusable.md.
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 · 98 lines · 1,266 tokens per session scan A ddb116a5846e
geogram AGENTS.md is an instructions file published in the GitHub repository geograms/geogram (24 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,266 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 2026-08-30.
Other instructions, from other repositories
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.