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/contentful/contentful.py/agents-mdgit clone --depth 1 https://github.com/contentful/contentful.pyWhat 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 | $0.00874 | $0.00874 |
| Opus 5 | $0.00437 | $0.00437 |
| Sonnet 5 | $0.00175 | $0.00175 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
contentful.py 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide
Read this file first. It tells you where to find context in this repo.
Quick Reference
| What you need | Where to look |
|---|---|
| What this repo is and how it works | ARCHITECTURE.md |
| How to build, test, and contribute | CONTRIBUTING.md |
| Why architectural decisions were made | docs/ADRs/ |
| What this repo does (user-facing) | README.rst |
| PR review rules | .bito/guidelines/ |
| Active specs / in-progress work | AI_CONTEXT/specs/ |
Sharp Edges & Invariants
- This is a CDA/CPA client only. Never add write operations (create, update, publish, delete). Those belong in
contentful-management.py. Any PR adding a CMA endpoint should be rejected. pdm.lockis the source of truth for dependencies. Do not hand-edit it. Regenerate withpdm lock -dif stale. Committing a lockfile with broken groups causes release failures.- Everything under
docs/exceptdocs/ADRs/is auto-generated Sphinx HTML — never hand-edit it. It is rebuilt bypdm run git-docson every release, which empties every entry directly underdocs/apart fromdocs/ADRs/. Decision records live indocs/ADRs/and are the one hand-authored thing there; specs live inAI_CONTEXT/specs/. contentful/__init__.py::__version__is the version source. PDM reads it dynamically. Update here before releasing — do not updatepyproject.tomldirectly.- VCR cassettes are recorded fixtures, not mocks. Cassettes in
fixtures/**/*.yamlare generated from real API responses. Hand-editing them breaks test replay. Re-record by deleting the cassette and running the test with live credentials. - Default HTTP timeout is 1 second. This is intentional and documented in the
Clientdocstring. Do not raise it without user-visible opt-in; it is a breaking change for users who rely on the current behavior. - Link resolution depth is capped at 20.
max_include_resolution_depth=20prevents stack overflows on circular content graphs. Do not remove this cap. - This repo is in limited/best-effort maintenance mode. New features should be scrutinized carefully against the strategic direction (future transition to generated SDKs from OpenAPI). Prefer bug fixes and security patches over new capabilities.
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 · 53 lines · 874 tokens per session scan A 558434525a48
contentful.py AGENTS.md is an instructions file published in the GitHub repository contentful/contentful.py (47 stars, last pushed 4d ago), licensed MIT. It adds 874 tokens to every session, about $0.0044 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
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).
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.
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.