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/langchain-ai/deepagents/agents-mdgit clone --depth 1 https://github.com/langchain-ai/deepagentsWhat 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 | $0.02268 | $0.02268 |
| Opus 5 | $0.01134 | $0.01134 |
| Sonnet 5 | $0.00454 | $0.00454 |
| Haiku 4.5 | $0.00227 | $0.00227 |
Grade A, and why
deepagents 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Global development guidelines for the Deep Agents monorepo
This file contains repository-wide rules for agents and contributors. Use these sources for details instead of duplicating them here:
libs/DEVELOPMENT.md— repository layout, setup, commands, pre-commit, the edit-test-lint loop, testing, and benchmarks.libs/ARCHITECTURE.md— runtime structure and SDK starting points..github/RELEASING.md— releases, version lines, fan-out, CI labels, and troubleshooting.- LangChain contributing guide — general contribution policy.
Corridor security analysis
When Corridor's analyzePlan tool is available, create a plan and use the tool to analyze it before generating or modifying code. Apply the resulting security guidance before writing code.
Development workflow
Work inside the package you are changing; libs/DEVELOPMENT.md covers environment setup (uv, make) and the edit-test-lint loop.
Do not add dependencies unless required. When adding one, justify its maintenance, adoption, and release activity.
Suppressing ruff rules
Use inline # noqa: RULE with a justification for individual exceptions. Reserve [tool.ruff.lint.per-file-ignores] for categorical policies that apply to a whole class of files, such as tests not requiring docstrings. Do not hide a single violation with a file-wide ignore. If you cannot justify a suppression, the code is probably the problem. See libs/DEVELOPMENT.md for worked examples.
PR conventions
Titles and scope
Follow Conventional Commits and include a scope. Allowed types and scopes are defined in .github/workflows/pr_lint.yml.
- Start the text after
type(scope):with a lowercase letter unless it begins with a proper noun or named code entity. - Wrap class, function, method, parameter, and variable names in backticks.
- Do not put Linear issue-closing markers in titles; put issue relationships in the PR body.
- For version-branch syncs, use
chore(repo): sync main into vX.Y;releaseis a type, not a scope. - Keep each bump-worthy PR to one releasable component. Put cross-package dependency or lockfile churn in a separate
chore(deps):PR. See multi-component fan-out and lockfile churn fan-out.
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 First seen · 155 lines · 2,268 tokens per session scan A 46b5bf4789af
deepagents AGENTS.md is an instructions file published in the GitHub repository langchain-ai/deepagents (28,825 stars, last pushed yesterday), licensed MIT. It adds 2,268 tokens to every session, about $0.0113 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
flock AGENTS.md
Instructions for Onelevenvy/flock, covering agents.md, project overview, build & development commands, rust backend and build the cli.
dawnai AGENTS.md
Instructions for cacheplane/dawnai, covering agents.md, what this is (and isn't), workspace map, definition of done and conventions.
TradingAgents-Telegram CLAUDE.md
Instructions for IvanWng97/TradingAgents-Telegram, covering tradingagents-telegram — architecture reference, layout, architecture (for code reviewers), request lifecycle (manual /watch tap) and state ownership.
daiv AGENTS.md
Instructions for srtab/daiv, covering agents.md, commands (verified), single test / pattern, translations and repo map (only what's non-obvious).
openharness AGENTS.md
Instructions for mifunedev/openharness, covering open harness — orchestrator, what open harness is, 1. agent work stays inside the sandbox, 2. coding-harness choice does not change the workspace and 3. remote and unattended operation are normal.
fullstack-langgraph-nextjs-agent CLAUDE.md
Instructions for agentailor/fullstack-langgraph-nextjs-agent, covering claude.md, essential development commands, setup (requires postgres and minio running), development and database.