Borrowing it
Nothing to install: this file belongs to AaravKashyap12/advise-project-approach. 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/AaravKashyap12/advise-project-approach/main/AGENTS.mdgit clone --depth 1 https://github.com/AaravKashyap12/advise-project-approachWrote 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/aaravkashyap12/advise-project-approach/agents-md)<a href="https://agentmods.dev/instructions/aaravkashyap12/advise-project-approach/agents-md"><img src="https://agentmods.dev/badge/instructions/aaravkashyap12/advise-project-approach/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/aaravkashyap12/advise-project-approach/agents-md"><img src="https://agentmods.dev/badge/instructions/aaravkashyap12/advise-project-approach/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 | $0.00929 | $0.00929 |
| Opus 5.5 | $0.00372 | $0.00372 |
| Sonnet 5.5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
advise-project-approach 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidance
This repository packages one public skill: advise-project-approach.
Source of Truth
- Edit the runtime skill at
skills/advise-project-approach/SKILL.md. - Do not edit
dist/advise-project-approach.skillby hand. Rebuild it withpython scripts/package_skill.py. - Keep
.claude-plugin/plugin.json,skills/advise-project-approach/agents/openai.yaml,CHANGELOG.md, and release notes in sync when changing their public metadata.
Release Discipline
- Treat
VERSIONas the canonical release version. - Every public push must bump
VERSIONusing semantic versioning, update.claude-plugin/plugin.json, replace the README's single currentWhat's Newsection and release-asset link, and add a dated entry toCHANGELOG.md. - Rebuild
dist/advise-project-approach.skillbefore committing. - After pushing, create or update the matching
vX.Y.ZGitHub release and attach the rebuilt.skillartifact. - Do not accumulate old release summaries in the README; keep full history in
CHANGELOG.md.
Maintainer Agent Roles
- For each PR or issue task, create a fresh read-only communication sub-agent with the complete discussion, review, check, and linked-issue context. Use it to recommend or draft communication, then close it when the task is complete.
- Keep communication review separate from code review. Use an independent code-review sub-agent to inspect correctness, regressions, compatibility, security, and missing tests.
- Communication agents must not post, close, merge, label, or otherwise mutate GitHub without explicit maintainer authorization.
- Read the full conversation before replying, distinguish a useful idea from implementation quality, and credit ideas incorporated through a different implementation.
- A green check is necessary but not sufficient for merging. Accepted changes must also satisfy scope, behavior, compatibility, documentation, and release requirements.
Validation
Install developer-only dependencies with python -m pip install -r requirements-dev.txt. They are not runtime requirements for people using the packaged skill.
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 · +12 lines · +137 tokens per session 86ebc4e8865f
- 1mo ago First seen · 64 lines · 792 tokens per session scan A d1639bbeb494
advise-project-approach AGENTS.md is an instructions file published in the GitHub repository AaravKashyap12/advise-project-approach (323 stars, last pushed 1mo ago), licensed MIT. It adds 929 tokens to every session, about $0.0037 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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.