Borrowing it
Nothing to install: this file belongs to incubateur-ademe/benefriches. 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/incubateur-ademe/benefriches/main/.claude/commands/adw-plan.mdgit clone --depth 1 https://github.com/incubateur-ademe/benefrichesWrote 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/incubateur-ademe/benefriches/adw-plan)<a href="https://agentmods.dev/commands/incubateur-ademe/benefriches/adw-plan"><img src="https://agentmods.dev/badge/commands/incubateur-ademe/benefriches/adw-plan/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/commands/incubateur-ademe/benefriches/adw-plan"><img src="https://agentmods.dev/badge/commands/incubateur-ademe/benefriches/adw-plan.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 | $0.00015 | $0.00503 |
| Opus 5.5 | $0.00006 | $0.00201 |
| Sonnet 5.5 | $0.00003 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
adw-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 9d 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.
What it actually says
Plan the issue snapshotted in $ARGUMENTS (written by linear.mjs snapshot) and write the spec to $ARGUMENTS/spec.md. Do not edit anything else: planning changes no code.
- Read every file in the snapshot:
issue.md,issue.json,comments.json,relations.json,DESIGN.mdif present, and each file inattachments/. The issue and its comments are the ticket;DESIGN.mdis the context of the project it belongs to. - Ground the plan in the code. Use the shell, Explore subagents for broad searches, and the docs MCP server for library APIs. Read the AGENTS.md files, rules and skills that apply to the files you will touch, so the Approach follows them instead of restating them.
- Decide everything the codebase lets you decide, and record each non-obvious choice in Approach. Never invent what only a human can provide: user-facing copy, a visual design for new UI, a business formula or threshold, an external API contract. If the ticket needs one of these and neither the snapshot nor the code provides it, the issue is blocked.
If blocked, write spec.md as the line BLOCKED followed by one bullet per missing input (what is missing, where it is needed, who can provide it) and stop. Otherwise write spec.md with exactly these sections, then print its path:
# <issue identifier>: <issue title>
## Context
Why this change, what exists today, and the constraints from the ticket and DESIGN.md.
## Approach
The design in a few paragraphs: layers touched, data flow, decisions and their reasons, the project skills the build must use (by name).
## Files
One bullet per file to create, modify or delete, with the change in one line.
## Validation
Shell commands, run from the repository root, that prove the change works: focused unit and integration tests, e2e specs, then `pnpm verify`. List the tests to add as `.claude/rules/testing.md` asks.
## Scenarios
User-visible checks QA walks in a browser, one per bullet: starting page, actions, expected result. Write `None` when nothing user-visible changes.
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.
- 9d ago First seen · 38 lines · 15 tokens per session scan A 636ce52764ec
adw-plan is a command published in the GitHub repository incubateur-ademe/benefriches (45 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 503 once invoked, about $0.0001 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 2026-10-21.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
sync-linear
Sync current work with Linear ticket status.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.