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 commands/eddacraft/anvil-plan-spec/plangit 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/commands/eddacraft/anvil-plan-spec/plan)<a href="https://agentmods.dev/commands/eddacraft/anvil-plan-spec/plan"><img src="https://agentmods.dev/badge/commands/eddacraft/anvil-plan-spec/plan.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 | $0.00000 | $0.00613 |
| Opus 5 | $0.00000 | $0.00307 |
| Sonnet 5 | $0.00000 | $0.00123 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
plan 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- plan — 100% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/plan
Start or continue APS planning for this project.
Instructions
You are starting an APS (Anvil Plan Spec) planning session. Follow these steps:
Step 1: Assess current state
Check what APS artefacts already exist:
- Look for
plans/directory - Read
plans/aps-rules.mdif it exists (agent guidance) - Read
plans/index.aps.mdif it exists (current plan) - Check
plans/modules/for existing module specs - Check for any work items with Ready or In Progress status
Step 2: Bootstrap if needed
If no plans/ directory exists, scaffold the APS structure before
continuing:
- Check if
scaffold/init.shexists in this repo — if so, run it:bash scaffold/init.sh . - Otherwise, create the structure manually:
mkdir -p plans/modules plans/execution plans/decisions- Create
plans/index.aps.mdwith an Index template - Create
plans/aps-rules.mdwith agent guidance
- Tell the user what was created and ask what they're building
If hooks aren't installed, suggest:
./aps-planning/scripts/install-hooks.sh
Step 3: Report what you found
Tell the user:
- Whether APS is already set up in this project
- What plans/modules exist and their current status
- What work items are in progress or ready
- What the logical next step is
Step 4: Help plan
Based on what the user needs:
If plans exist but are empty: Ask what they're building and help create the right spec. Use the template picker:
| Situation | Template |
|---|---|
| Quick feature (1-3 items) | Simple spec |
| Module with boundaries | Module spec |
| Multi-module initiative | Index + Modules |
If plans exist but need work items: Help define work items with Intent, Expected Outcome, and Validation fields.
If work items are Ready: Ask which to start executing. Create an Action Plan if the work item is complex.
If work items are In Progress: Pick up where the last session left off. Re-read the work item and continue.
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 · 82 lines · 0 tokens per session scan A 9e6ea0c26b3f
plan is a command published in the GitHub repository eddacraft/anvil-plan-spec (10 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 613 tokens. 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.