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 3awny/qship --skill qshipphasecheckgit clone --depth 1 https://github.com/3awny/qshipWrote 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/3awny/qship/qshipphasecheck)<a href="https://agentmods.dev/skills/3awny/qship/qshipphasecheck"><img src="https://agentmods.dev/badge/skills/3awny/qship/qshipphasecheck/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/skills/3awny/qship/qshipphasecheck"><img src="https://agentmods.dev/badge/skills/3awny/qship/qshipphasecheck.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 | $0.00062 | $0.01777 |
| Opus 5 | $0.00031 | $0.00889 |
| Sonnet 5 | $0.00012 | $0.00355 |
| Haiku 4.5 | $0.00006 | $0.00178 |
Grade A, and why
qshipphasecheck 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 10d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qshipphasecheck — Inter-Phase Hard Gate
This skill is a BLOCKING GATE. If it fails, the next phase MUST NOT start.
Unlike qshipcheck (which runs at the end and can only report), qshipphasecheck runs BETWEEN phases and BLOCKS progression. It is the architectural enforcement layer that ensures no phase is skipped regardless of what the LLM thinks.
⛔ AUTONOMY & PERSISTENCE CONTRACT
A FAIL verdict is NOT a terminal state for the pipeline. It is an instruction to:
- Dispatch the missing agents/skills for each FAIL row.
- Wait for their results.
- Re-run
/qshipphasecheckfor the same phase. - Repeat with no iteration cap until PASS.
Anthropic official guidance (verbatim):
Never artificially stop any task early regardless of the context remaining.
The orchestrator MUST NOT skip to the next phase while this skill reports FAIL, and MUST NOT abandon the pipeline because a FAIL loop has run several rounds. Loop until PASS.
When to Run
The qship orchestrator MUST invoke this at two transition points:
| Transition | Command | What it validates |
|---|---|---|
| Phase 2 → Phase 3 | /qshipphasecheck phase2 <TICKET_IDS> |
ALL Phase 2 steps (7.5–11.5) completed for EVERY ticket |
| Phase 3 → Phase 4 | /qshipphasecheck phase3 <TICKET_IDS> |
Phase 3 (E2E testing) completed |
If qshipphasecheck reports FAIL, the orchestrator MUST:
- Execute the missing steps
- Re-run qshipphasecheck
- Only proceed to the next phase after PASS
Phase 2 Validation (phase2)
Read the progress tracker for EACH ticket:
{{STATE_ROOT}}/worktrees/<TICKET_ID>/phase2-progress.md
Required Steps — ALL must be DONE:
| Step | Required Evidence | Why it can't be skipped |
|---|---|---|
| 7.5 Simplify | Agent dispatch + result | Simplification before review reduces noise |
| 8 Review (3 agents) | 3 Task dispatches + results | Each reviewer checks different aspects |
| 9 Bug Hunt (5 agents) | 5 Task dispatches + results | Different bug types need different detectors |
| 10 qbcheck | Skill invocation + validation counts | Separates real bugs from false positives — Step 11 input depends on this |
| 11 Fix Issues | Commits OR "0 real bugs" | Validated bugs must be fixed |
| 11.5 Verification | pytest output + formatting check | Confirms fixes didn't break anything |
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.
- 10d ago First seen · 167 lines · 62 tokens per session scan A d9a946fa1ab4
qshipphasecheck is a skill published in the GitHub repository 3awny/qship (2 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 1,777 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
prompt-pilot
Rewrite a rough, vague prompt into a precise, context-enriched prompt. Explores the codebase read-only and weaves real file paths and symbols into the rewritten prompt — never implements the task itself. Use when the user asks to optimize, enrich, or improve a prompt before running it.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
architecture-design
Use only when creating new registrable ML components that require Factory or Registry patterns.
results-analysis
This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.