Borrowing it
Nothing to install: this file belongs to anton-abyzov/specweave. 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/anton-abyzov/specweave/develop/AGENTS.mdgit clone --depth 1 https://github.com/anton-abyzov/specweaveWrote 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/anton-abyzov/specweave/agents-md)<a href="https://agentmods.dev/instructions/anton-abyzov/specweave/agents-md"><img src="https://agentmods.dev/badge/instructions/anton-abyzov/specweave/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/anton-abyzov/specweave/agents-md"><img src="https://agentmods.dev/badge/instructions/anton-abyzov/specweave/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 | $0.01511 | $0.01511 |
| Opus 5.5 | $0.00604 | $0.00604 |
| Sonnet 5.5 | $0.00302 | $0.00302 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
specweave 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 5d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SpecWeave (this repository)
This is the source of the specweave npm package: a CLI plus a Claude Code plugin that plans work as increments (spec.md + ledger.jsonl) and hands it between AI tools. This file is for anyone changing SpecWeave itself; the file SpecWeave writes into user projects is src/templates/AGENTS.md.template.
Layout
| Path | What it is |
|---|---|
bin/specweave.js |
Commander entry; each command lazily imports dist/src/cli/commands/<name>.js |
src/cli/commands/ |
One file per CLI command |
src/core/tasks/ |
Task parser, ledger.jsonl fold, task board, verify, AC derivation |
src/core/session/ |
pickup, handoff (doc, Git capture, --push, secret scrub) |
src/core/increment/ |
Increment creation, metadata, status transitions |
src/core/hooks/handlers/ |
Claude Code hook handlers, reached through plugins/specweave/hooks/run.mjs |
src/sync/, src/integrations/ |
GitHub, Jira and ADO sync (opt-in, only on specweave sync) |
src/templates/ |
What init and update write into user projects |
skills/sw-* |
The one skill source for every tool; npm run generate:skills writes the plugin copies in plugins/specweave/skills/ (never edit those) |
docs-site/ |
spec-weave.com (Docusaurus); deploys from develop |
Work here
- Node 22.
npm ci, thennpm run build(tsc, dashboard, plugin copies). The CLI runs fromdist/, so rebuild before trying a command:node bin/specweave.js <cmd>. - Tests:
npm run test:unitis what CI runs (tests/unit/**). Co-locatedsrc/**/*.test.tsfiles are not in CI; run them withnpx vitest run src/<path>when you touch that code, and put new tests undertests/unit/. - Typecheck with
npx tsc --noEmit -p .before pushing. - Adding or renaming a CLI command or option: regenerate completions with
node scripts/completions/generate.mjs. initrefuses to run inside the system temp directory; use a scratch folder elsewhere to try it.- Keep files under 1,500 lines. Prefer deleting code to adapting it.
- Default branch is
develop. PRs targetdevelop. - Browser tests and automation must use headless Chrome/Playwright CLI. Set
headless: true,PWDEBUG=0,PLAYWRIGHT_HTML_OPEN=never, and HTML reportsopen: 'never'. Save captures to files and pass this rule to subagents. If a visible browser is essential, ask the user and wait for explicit approval before opening it; a headless failure is not approval.
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.
- 5d ago Changed · +2 lines · +249 tokens per session 8054e9aae5b4
- 7d ago Changed · +10 lines · +168 tokens per session f0e72812297c
- 8d ago Changed · +1 lines · +86 tokens per session 471430c637b1
- 13d ago Changed · +2 lines · +89 tokens per session 4d1908ed44bc
- 18d ago Changed · +1 lines · +118 tokens per session cf573627e0cf
- 26d ago Changed · -385 lines · -3,149 tokens per session 5b894fd24e43
- 1mo ago Changed · -22 lines · -100 tokens per session 7ce1a77077c1
- 1mo ago First seen · 447 lines · 4,050 tokens per session scan A c6301f38334e
specweave AGENTS.md is an instructions file published in the GitHub repository anton-abyzov/specweave (166 stars, last pushed today), licensed MIT. It adds 1,511 tokens to every session, about $0.0060 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.