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 skills add ChianW/C31 --skill gsd-shipgit clone --depth 1 https://github.com/ChianW/C31Wrote 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/skills/chianw/c31/gsd-ship)<a href="https://agentmods.dev/skills/chianw/c31/gsd-ship"><img src="https://agentmods.dev/badge/skills/chianw/c31/gsd-ship.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 5.1 | $0.00064 | $0.00881 |
| Opus 5 | $0.00032 | $0.00441 |
| Sonnet 5 | $0.00013 | $0.00176 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
gsd-ship 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 7d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multilingual Triggers
| Language | Trigger phrases |
|---|---|
| EN | gsd-ship |
| ZH | 收尾, 交付, 上线 |
| JA | リリース, 完成, デプロイ |
Output language: Respond automatically in the user's conversation language.
gsd-ship — Deliver & Close
Finalize a completed phase or entire project. Confirm acceptance, generate deliverable summary, update project state, and archive.
Preconditions
- All verification (C31-review or C31-review) has passed
- No unresolved blockers in STATE.md
- User confirms readiness to ship
Workflow
Phase 1: Load & Assess
- Read
memory/.planning/STATE.md - Read
memory/.planning/ROADMAP.md - Identify:
- Current phase number and name
- Phase status (must be "verified" or later)
- List of deliverables produced
- Blocker status (must be empty or resolved)
Phase 2: Acceptance Checklist
Walk through each deliverable with user:
Ship Checklist for Phase XX — <phase_name>
Deliverables:
[ ] <deliverable_1> — <brief_description>
[ ] <deliverable_2> — <brief_description>
...
Verification:
[ ] All tests passing (or UAT signed off)
[ ] Code reviewed (C31-review completed)
[ ] Documentation updated
[ ] No regressions identified
Blockers:
(none or list resolved status)
Ship? [yes] [no] [hold]
If user selects [no] or [hold], stop. Update STATE.md with reason.
Phase 3: Generate Summary
Create memory/.planning/phases/XX-SUMMARY.md:
# Phase XX Summary — <phase_name>
## What Was Done
- <achievement_1>
- <achievement_2>
## Key Decisions
- D-01: <decision> (from CONTEXT.md)
- D-02: <decision>
## Deliverables
- <file/link_1>
- <file/link_2>
## Verification
- Reviewer: <reviewer_name>
- Result: PASS / PARTIAL / FAIL (with notes)
## Time
- Started: <date>
- Shipped: <date>
Phase 4: Update STATE.md
Current Position → Next phase (or "COMPLETE" if last phase)
Phase XX status: shipped
Phase 5: Update ROADMAP.md
Mark phase as ✅ shipped. If all phases shipped, mark milestone as ✅.
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.
- 7d ago First seen · 154 lines · 64 tokens per session scan A a3fc6d533f2a
gsd-ship is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 12d ago), licensed MIT. It adds 64 tokens to every session and 881 once invoked, about $0.0003 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 skills, from other repositories
agent-sync-coordinator
Agent skill for sync-coordinator - invoke with $agent-sync-coordinator.
agent-multi-repo-swarm
Agent skill for multi-repo-swarm - invoke with $agent-multi-repo-swarm.
agent-swarm-issue
Agent skill for swarm-issue - invoke with $agent-swarm-issue.
agent-issue-tracker
Agent skill for issue-tracker - invoke with $agent-issue-tracker.
agent-project-board-sync
Agent skill for project-board-sync - invoke with $agent-project-board-sync.
agent-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.