Borrowing it
Nothing to install: this file belongs to AndreVianna/aid-methodology. 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/AndreVianna/aid-methodology/master/AGENTS.mdgit clone --depth 1 https://github.com/AndreVianna/aid-methodologyWrote 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/andrevianna/aid-methodology/agents-md)<a href="https://agentmods.dev/instructions/andrevianna/aid-methodology/agents-md"><img src="https://agentmods.dev/badge/instructions/andrevianna/aid-methodology/agents-md.svg" alt="Measured on agentmods" 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 | $0.01535 | $0.01535 |
| Opus 5 | $0.00767 | $0.00767 |
| Sonnet 5 | $0.00307 | $0.00307 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade A, and why
aid-methodology 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- aid-methodology CLAUDE.md — 91% identical, 24 lines differ
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
(pending discovery)
Tracking discipline (IMPERATIVE)
Every project, task, and deliverable is tracked in a state file — the work's
.aid/works/work-NNN-*/STATE.md (plus .aid/knowledge/STATE.md for knowledge-base and
cross-phase process state). Keeping it current is not optional:
- ANY and ALL changes to the state of a project, task, or deliverable — status, phase, grade, review outcome, or artifacts produced — MUST be written to the proper tracking file IMMEDIATELY, as part of the same action that made the change. Untracked work is incomplete work.
- This binds EVERY agent, without exception — whether invoked by a SKILL or by a DIRECT PROMPT, and whether on the FULL or the LITE path.
- If no tracking file exists for the work yet, create it first (from the work-state template) before doing anything else.
- Task execution is the sharpest case of this rule. During
/aid-execute, a task'sStateMUST be written the instant it changes —In Progressat the start of EXECUTE,In Reviewbefore the reviewer is dispatched, and a terminal value (Done/Failed) at the end (Blockedis a distinct, orchestrator-assigned value for a DIFFERENT, downstream task that depends on a failed one — never self-written by the task being executed). This binds whoever executes the task — the main/orchestrator agent executing it DIRECTLY (not only a dispatched sub-agent) MUST perform these writes itself, at the same points, with no exception and no bypass. A task that sits atPendingin the dashboard for its entire execution and then jumps straight toDoneis exactly the failure mode this rule exists to prevent. - Work folders are transient.
.aid/works/work-NNN-*/holds disposable per-work pipeline state and may be pruned once the work ships. No permanent artifact — product code,canonical/content (or itsprofiles/render), tests, docs, the Knowledge Base, or these context files — may depend on the contents of a specific work folder: tests build their own fixtures, and the KB never cites a work folder as a source. Pipeline skills/scripts that create, read, or update work folders as live runtime state are exempt. - Never name a work in the Knowledge Base.
.aid/knowledge/**must contain no work id and no work-folder path — notwork-042, not.aid/works/work-042-*/, not "specified by work-042" or "added in work-042" — in prose, tables, headings, or frontmatter. Two reasons, each sufficient: a work folder is pruned when its work ships, so the cite is a dangling pointer by design; and the KB states only the current state of the project's sources, whereas which work produced a change is history. Cite the durable artifact the work left on disk instead. It follows that a KB doc carries no## Change Log/## Revision Historysection and nochangelog:frontmatter field — git records per-doc history with author, date, and diff, at higher fidelity and without drift. This binds.aid/knowledge/alone: skills, templates, and pipeline scripts name works legitimately, because they operate on them.
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 · 111 lines · 1,535 tokens per session scan A c09cfe7e1044
aid-methodology AGENTS.md is an instructions file published in the GitHub repository AndreVianna/aid-methodology (5 stars, last pushed yesterday), licensed MIT. It adds 1,535 tokens to every session, about $0.0077 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 2026-09-03.
Other instructions, from other repositories
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.
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.
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).
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.