Borrowing it
Nothing to install: this file belongs to sandeep84397/agent-brain. 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/sandeep84397/agent-brain/main/AGENTS.mdgit clone --depth 1 https://github.com/sandeep84397/agent-brainWrote 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/sandeep84397/agent-brain/agents-md)<a href="https://agentmods.dev/instructions/sandeep84397/agent-brain/agents-md"><img src="https://agentmods.dev/badge/instructions/sandeep84397/agent-brain/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/sandeep84397/agent-brain/agents-md"><img src="https://agentmods.dev/badge/instructions/sandeep84397/agent-brain/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 | $0.00434 | $0.00434 |
| Opus 5.5 | $0.00174 | $0.00174 |
| Sonnet 5.5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
agent-brain 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 1mo 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 — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository Expectations
- Use the installed brain venv for server commands when dependencies are not installed in the active shell:
~/.agent-brain/.venv/bin/python ~/.agent-brain/server.py <cmd>. - Run focused tests after changing setup, hooks, or compatibility helpers. For Codex compatibility, run
python3 -m unittest tests.test_codex_setup -v. - Keep setup commands idempotent. Re-running
./setup.sh --codex,./setup.sh --all, or project-link commands must not duplicate config blocks.
Agent Brain Protocol
- Reuse current repo context; call
get_roadmap(repo=...)for missing context andpre_check(repo=..., provider=...)before non-trivial implementation when Brain is available. - Before editing code, call
log_decisionso the choice is stored for later sessions. - Prefer
query_sanandget_san(file_path="<absolute path>")for code exploration when SAN briefs exist; use raw reads for exact edits, non-code files, or files without SAN. - After user review or test results, call
log_outcomewhen a decision id is available.
Provider-neutral resource discipline
- Choose the least expensive available route likely to meet acceptance criteria, considering uncertainty, consequences and validation difficulty. Preserve explicit user model choices.
- OpenAI starting routes: Luna low/medium for bounded mechanical work; Terra medium for routine implementation; Sol high for complex review/ambiguity; Astra medium/high for the hardest cross-system reasoning. Other providers use their configured capabilities; never silently cross providers.
- Routing is advice. Only verified host/profile settings establish actual model and effort. If unverified, report
Route plan:and the limitation; never claim a prompt switched models. - Escalate for reasoning difficulty, not missing information or broken environments. Max/Ultra require exceptional justification; parallel agents require independent bounded work whose benefits exceed coordination cost.
- Reuse verified findings and exact test evidence. Stop when acceptance criteria and required checks pass. Report measured usage only; missing data stays unknown.
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.
- 1mo ago Changed · +8 lines · +193 tokens per session 6273c6431967
- 1mo ago First seen · 15 lines · 241 tokens per session scan A cfa34ded3602
agent-brain AGENTS.md is an instructions file published in the GitHub repository sandeep84397/agent-brain (11 stars, last pushed 1mo ago), licensed MIT. It adds 434 tokens to every session, about $0.0017 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 2026-08-31.
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.