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/contextgeneric/cgp/agents-mdgit clone --depth 1 https://github.com/contextgeneric/cgpWhat 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 | $0.05994 | $0.05994 |
| Opus 5 | $0.02997 | $0.02997 |
| Sonnet 5 | $0.01199 | $0.01199 |
| Haiku 4.5 | $0.00599 | $0.00599 |
Grade A, and why
cgp 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 — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to LLM agents when working with code in this repository.
Project status
This working tree is the upcoming v0.8.0 release. Every crate under crates/ is
versioned 0.8.0-alpha in its Cargo.toml — the pre-release of v0.8.0 — and the documentation in the
knowledge base already refers to
the current version as v0.8.0, so nothing needs a version edit when v0.8.0 ships.
The stable release on crates.io is still v0.7.0, and it is not compatible with this tree. v0.7.0 carries legacy features and syntax that v0.8.0 has removed or changed, so code or documentation written against v0.7.0 will not compile here. Treat crates.io v0.7.0 as a separate, older line and do not reconcile this tree's syntax against it.
Only the library crates are published. The five crates under crates/tests/ are
marked publish = false, so cargo publish --workspace skips them and publishes just the real CGP
crates.
The sibling projects
cgp is one repository in a family that is developed together, so a task here routinely reads — and
often updates — another one. sibling-projects.md is the authoritative list:
where each project lives, which revision of it to read, and the rules for finding a sibling locally
versus linking to it. Three of them matter constantly.
This repository's documentation lives in cgp-knowledge-base.
There is no docs/ directory here. The construct reference, the concepts, the guides, the error
catalog, and the macro-implementation notes are all in that repository's
cgp/ directory, and the worked
examples sit at its top level. It is a consolidated base — cargo-cgp's documentation is the
neighbouring section — which is why an error class here and the tool's handling of it are now one
directory apart. Treat the knowledge base as part of this repository's surface: a change to a
construct's behavior carries its documentation change, and when the checkout is missing, say plainly
what needs updating there.
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 · 335 lines · 5,994 tokens per session scan A fe648963752f
cgp AGENTS.md is an instructions file published in the GitHub repository contextgeneric/cgp (248 stars, last pushed 29d ago), licensed Apache-2.0. It adds 5,994 tokens to every session, about $0.0300 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
agentgateway copilot-instructions.md
Instructions for agentgateway/agentgateway: Do not check for, speculate about, or report compilation errors during code review. Compilation diagnostics from review are frequently incorrect; rely on CI to detect and report compilation failures.
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.
terminal-browser AGENTS.md
Instructions for zenbu-labs/terminal-browser, a project described as: A browser inside your terminal.
openapi AGENTS.md
Instructions for longbridge/openapi, covering agent guidelines, after modifying rust code, after modifying the node.js sdk (nodejs/), after modifying the python sdk api (python/) and after modifying the c sdk (c/).
playwright-rust CLAUDE.md
Instructions for padamson/playwright-rust, covering claude.md, project, repository layout, skills (procedural reference) and documentation hierarchy.
flox AGENTS.md
AGENTS.md instructions for flox/flox, covering claude.md, project overview, development setup, already in dev shell (innixshell is set) — run directly and not in dev shell — wrap with nix develop -c.