Start a session from what was left - trace saves, briefs, proposals, review reports, issues - and ask what to continue. Never resume or implement automatically.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Run scripts/scan.cjs from the intended repository, not the launch directory
by assumption. --json is for tooling; --all includes completed work. In
Claude Code pass --claude-code, so commands come out callable
(/ship:ship). The scanner recognizes shipped markers as terminal.
Next is the start of a session; trace ends one. When the scan opens with
a Next: line from the newest trace save, offer it first: ask only « On
reprend : <its next> ? » in the conversation language and wait. On yes,
run scripts/scan.cjs --resume <its date> and hand that next action to
Arsenal. On no, or without such a line, show the numbered list of open
saves, review reports and issues (for each save, what was done and what is
left), ask only « On continue quoi ? » and wait. In Claude Code and Codex
the SessionStart hook prints the same with this instruction after
/clear; elsewhere the user runs next.
When the user picks a session save, run scripts/scan.cjs --resume <its date> so it is not offered again, then hand its next line to
Arsenal, which picks the skill and keeps its approval gates. A picked spec,
review or issue goes to Arsenal the same way. Next never starts the work.
Report the most useful open action. Do not re-read every artifact body after a sufficient scan. Read a specific artifact only for a requested detail. Distinguish implemented work waiting for user acceptance from work to redo. An old todo or reminder is not evidence that a completed fix needs another diagnosis. Never execute the recommended action without a user request.
Return the open-work result to Arsenal when it called this skill. A request to resume work authorizes Arsenal to inspect the selected artifact and choose the next step; a status-only request stops here. Never reopen shipped work.
Work solo. Ask before any subagent or reviewer, even in auto mode. Explain the independent scope and expected benefit first. No hidden advisor, nested delegation, model retuning, repeated successful checks, or progress spam. Use existing context before asking questions. Stop when the requested result is delivered. User stops and scope changes override pending steps.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when the user invokes Arsenal, needs help choosing an approach, or wants an end-to-end task handled with the installed Arsenal skills.
The English summary is being prepared. Showing the original description.
Write a product brief and its task list when the user requests a product specification. Never implement it.
The English summary is being prepared. Showing the original description.
Create, update or resume a GitHub or Linear issue as durable resolution memory when requested.
The English summary is being prepared. Showing the original description.
Design a concrete technical proposal with evidence and tradeoffs when a decision needs design. No implementation or automatic reviewer.
The English summary is being prepared. Showing the original description.
Deep code review driven by a short interview. Read-only reader agents analyze the chosen scope per angle, the lead verifies every finding, and each point is routed to the skill that fixes it. Never edits the code.
The English summary is being prepared. Showing the original description.
Implement a clear request or an approved brief/proposal. Work solo, make the smallest sufficient change, verify the changed behavior, and stop. Ask before any delegation.
The English summary is being prepared. Showing the original description.