Borrowing it
Nothing to install: this file belongs to sawrus/agent-guides. 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/sawrus/agent-guides/main/AGENTS.mdgit clone --depth 1 https://github.com/sawrus/agent-guidesWrote 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/sawrus/agent-guides/agents-md)<a href="https://agentmods.dev/instructions/sawrus/agent-guides/agents-md"><img src="https://agentmods.dev/badge/instructions/sawrus/agent-guides/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/sawrus/agent-guides/agents-md"><img src="https://agentmods.dev/badge/instructions/sawrus/agent-guides/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 | $0.00733 | $0.00733 |
| Opus 5.5 | $0.00293 | $0.00293 |
| Sonnet 5.5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
agent-guides 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 yesterday.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS — core guidance
This file loads into every session and every subagent. Keep it short. Put details in skills, scoped rules, and workflows.
Load on demand
- Read a rule, skill, workflow, or prompt only when the task touches its subject. Rules live in
.agent/rules/; read one when a loaded skill or workflow links it. Claude Code loads.claude/rules/itself. - Run a workflow from
.agent/workflows/<name>.mdonly for its command. - Before changing project logic, read the matching design or behavior page under
docs/**, if one exists.
Scale the process to the task
- Trivial (a question, a one-line fix): act directly. No plan, no subagents, no extra documents.
- Small (one module, clear cause): no subagents. Make the change, run the checks, report.
- Feature or multi-module change: first state acceptance criteria and what is out of scope. Use one read-only explorer subagent (ours or the host's native one) only when the code is unfamiliar and too large to list with one command. After a multi-module diff, use one reviewer subagent (host-native or installed) only for correctness bugs and unmet requirements. A one-module feature needs none.
- Do not start a subagent for work that one tool call can do.
- Workflow roles (
product-owner,developer,qa, and others) name responsibilities. Delegate a step to a role subagent only when that subagent is installed (teamprofile); otherwise do the step yourself.
Definition of done
- After the last edit, run the project checks (Makefile targets such as
make testandmake lint, or their documented equivalents). Show the command and its result. Do not claim success without that output. - Change only what the task needs. List unrelated problems in the report; do not fix them.
- A user-visible change updates
CHANGELOG.mdand the matchingdocs/page, if one exists. Bump the version and name the CHANGELOG section as the project's release policy says (for exampledocs/release-policy.md). Without a policy, write underUnreleased, and only a completed feature updates the project version. - Add a new file at the repository root only after the user approves its name and purpose.
- Never run write or maintenance SQL on a non-local database. Ask before using database credentials from
.env.
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.
- yesterday Changed · +1 lines · +23 tokens per session 0a64b2b0d872
- 2d ago Changed · +1 lines · +29 tokens per session 2a154a779377
- 6d ago Changed · -85 lines · -598 tokens per session f05b75ee6a13
- 14d ago Changed · +12 lines · +202 tokens per session 8288bd8ca5cf
- 20d ago Changed · +4 lines · +50 tokens per session 875234340122
- 1mo ago First seen · 121 lines · 1,027 tokens per session scan A 358859d35958
agent-guides AGENTS.md is an instructions file published in the GitHub repository sawrus/agent-guides (19 stars, last pushed today), licensed MIT. It adds 733 tokens to every session, about $0.0029 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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.