Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/eddacraft/anvil-plan-spec/agents-mdgit clone --depth 1 https://github.com/eddacraft/anvil-plan-specWrote 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/eddacraft/anvil-plan-spec/agents-md)<a href="https://agentmods.dev/instructions/eddacraft/anvil-plan-spec/agents-md"><img src="https://agentmods.dev/badge/instructions/eddacraft/anvil-plan-spec/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 | $0.00958 | $0.00958 |
| Opus 5 | $0.00479 | $0.00479 |
| Sonnet 5 | $0.00192 | $0.00192 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
anvil-plan-spec 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 4d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Anvil-Plan-Spec (APS) Collaboration Rules
This repo defines the Anvil Plan Spec format — templates, prompts, and examples for planning and task authorisation in AI-assisted development.
What this repo is
APS is a specification format, not executable code. It contains:
- Templates for plans, modules, work items, action plans, and design documents
- Prompts for AI agents
- Examples and documentation
- A CLI for validation (linting)
Execution authority
- Specs describe intent.
- Tasks authorise execution.
- If there is no task, do not implement changes unless explicitly instructed.
Rules for AI contributing to this repo
When modifying templates, prompts, or documentation:
- Keep templates minimal — avoid over-prescription
- Maintain consistency — field names, structure, and terminology
- Update examples when template structure changes
- Run markdownlint before committing (
npx markdownlint-cli "**/*.md")- CI automatically runs markdown linting on all PRs
Keeping the plans honest
This repo plans itself with APS (plans/index.aps.md). Plan updates are part of the change, not an afterthought — include them in the same commit/PR as the work they describe.
When a plan update is required
Update the matching plan whenever a change affects templates, prompts, examples, installer behaviour, or validation behaviour (the dogfood module's scope). Concretely:
- Executing a work item → its status, and
Results:for non-trivial items - Discovering new work → add a
Draftwork item to the owning module - Making a judgment call → record it in the module's
## Decisions - Hitting a bug or open question → log it in
plans/issues.md (
ISS-NNN/Q-NNN) - Finishing a module's last item → mark the module Complete, update the
index table, roll the task table into
plans/completed.aps.md
How to mark work item status
Prefer the CLI — it enforces the state machine and stamps dates:
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.
- 4d ago First seen · 106 lines · 958 tokens per session scan A 739752047c03
anvil-plan-spec AGENTS.md is an instructions file published in the GitHub repository eddacraft/anvil-plan-spec (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 958 tokens to every session, about $0.0048 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 2026-08-31.
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.