Borrowing it
Nothing to install: this file belongs to jrollin/cartog. 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/jrollin/cartog/main/AGENTS.mdgit clone --depth 1 https://github.com/jrollin/cartogWrote 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/jrollin/cartog/agents-md)<a href="https://agentmods.dev/instructions/jrollin/cartog/agents-md"><img src="https://agentmods.dev/badge/instructions/jrollin/cartog/agents-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/jrollin/cartog/agents-md"><img src="https://agentmods.dev/badge/instructions/jrollin/cartog/agents-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 | $0.13989 | $0.13989 |
| Opus 5.5 | $0.05596 | $0.05596 |
| Sonnet 5.5 | $0.02798 | $0.02798 |
| Haiku 4.5 | $0.01399 | $0.01399 |
Grade A, and why
cartog 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 3d 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines
Project
cartog — code graph indexer for LLM coding agents. Cargo workspace (11 published crates + cartog-loom-models, a test-only model-checking crate), tree-sitter parsing, SQLite storage.
See docs/product.md for product context, docs/tech.md for architecture decisions, docs/structure.md for module layout, docs/usage.md for CLI commands and MCP/skill setup.
Build & Test
cargo build # debug build
cargo build --release # release build
cargo test --workspace # run all tests (~600 tests across the 11 published crates)
cargo fmt --check # check formatting
cargo clippy --all-targets -- -D warnings # lint
Always run cargo fmt --check and cargo clippy --all-targets -- -D warnings before committing.
cargo check --no-default-features -p cartog-rag # verify builds without ONNX
cargo check --features provider-ollama -p cartog-rag # verify Ollama feature
cargo check --features provider-openai -p cartog-rag # verify OpenAI feature
Integrity checks
make check # all checks (Rust project + fixtures + skill + versions)
make check-rust # cargo fmt + clippy + test
make check-fixtures # validate all fixture codebases (py, ts, go, rs, rb, java, php, dart, swift, kt)
make check-fixtures-docker # same, forcing the Docker fallback for every language
make check-skill # skill tests (ensure_indexed.sh unit tests)
make check-versions # every version anchor release.sh bumps matches Cargo.toml
make check-flaky # repeat the full suite 4x (N=8 for more) to surface cross-test interference
make eval-skill # LLM-as-judge skill evaluation (requires claude CLI)
make eval-agents # LLM-as-judge agent evaluation (requires claude CLI)
make bench # shell benchmark suite (13 scenarios x 12 languages)
make bench-resolution # edge-resolution rate (heuristic + host LSP, all languages; saves a provenance snapshot)
make bench-resolution-docker # same, LSP servers via Docker images (all 16, strict — no host fallback); `make lsp-images` builds them
make bench-resolution-scale # synthetic N-vs-2N repo, asserts index time stays near-linear (quadratic-regression guard, cf. #110)
make bench-memory # guards `cartog serve` idle footprint (macOS `footprint` / Linux `smaps_rollup`; in CI)
make bench-criterion # ONNX-free criterion benches (queries, per-language indexing, hybrid search)
make bench-onnx # real-model embed/rerank benches (needs `cartog rag setup`; not in CI)
make bench-rag # RAG relevancy benchmarks (in-memory + shell scenario 13)
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.
- 3d ago Changed · +5 lines · +201 tokens per session 64c2a02f9690
- 4d ago Changed · +2 lines · +215 tokens per session 562ba96895cc
- 10d ago Changed · +1 lines · +112 tokens per session 7036baf6e43f
- 1mo ago Changed · +156 tokens per session 3d8ab68b63e7
- 1mo ago Changed · +50 lines · +3,716 tokens per session f8dc60bc9db8
- 1mo ago Changed · +42 tokens per session 9275e557bf2f
- 2mo ago First seen · 272 lines · 9,547 tokens per session scan A 1b68392f78d1
cartog AGENTS.md is an instructions file published in the GitHub repository jrollin/cartog (19 stars, last pushed 3d ago), licensed MIT. It adds 13,989 tokens to every session, about $0.0560 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 2026-08-30.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.