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 skills/3awny/qship/qplannpx skills add 3awny/qship --skill qplangit 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/qplan)<a href="https://agentmods.dev/skills/3awny/qship/qplan"><img src="https://agentmods.dev/badge/skills/3awny/qship/qplan.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 | $0.00057 | $0.02051 |
| Opus 5 | $0.00028 | $0.01026 |
| Sonnet 5 | $0.00011 | $0.00410 |
| Haiku 4.5 | $0.00006 | $0.00205 |
Grade A, and why
qplan 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 5d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Review
Review a proposed implementation plan against the codebase and surface gaps, risks, and pattern violations before any code is written. The output is a verdict + a punch list of changes the plan author should make — not a rewrite of the plan.
This is a reviewer, not a drafter. If no plan exists yet, ask the user for one (or for the Jira ticket / spec) before proceeding. Don't invent a plan and then "review" it — that defeats the purpose.
Inputs
Before reviewing, confirm what you're reviewing:
- The plan — a written plan in conversation, a markdown file, a Jira ticket description with steps, a Confluence page, or "the approach we just discussed". If unclear, ask.
- The source of truth for requirements — Jira ticket, spec, bug report, or user goal. Needed for the coverage check below. If absent, note it and skip the AC table.
- Scope hints — repos affected, branches in flight, deadlines. Ask only if non-obvious.
If the plan is too vague to review (e.g. "I'll add an endpoint and a UI"), say so and ask the author to flesh it out before you can usefully review.
Memory
MEMORY.md is already loaded by the auto-memory system — don't re-read it. Just check if any loaded entry is relevant (planning patterns, cross-repo gotchas, analogous-code lessons) and apply it. If a memory entry directly contradicts something in the plan, call it out in the review with a citation.
What a good plan looks like (the rubric)
Apply each of these to the plan. For every miss, add a row to the punch list with the specific change the author should make.
1. Analogous code was found and matched
The strongest signal a plan is grounded is that it points at an existing, similar implementation and proposes to follow it. If the plan doesn't cite an analogue, the author probably hasn't looked.
How to check: Search the codebase yourself for similar features (semantic search via mcp__claude-context-local__search_codebase, then verify with grep if you're skeptical). If you find an analogue the plan ignores, that's a finding — the plan should adopt the existing patterns (filters like is_active, tenant scoping, error handling, return shapes, thresholds) unless it explicitly justifies why it diverges.
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.
- 5d ago First seen · 138 lines · 57 tokens per session scan A 08256f40bb88
qplan is a skill published in the GitHub repository 3awny/qship (2 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 2,051 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
remove-ai-marks
Strip multi-vendor AI provenance from owned files: hidden Unicode (Layer A), statistical sampling watermarks via rewrite (Layer B — always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD. Covers Claude, Gemini/SynthID-class, OpenAI provenance surfaces, and open-LLM sampling…
clean-user-facing-text
Audit and finalize authorized natural-language text meant for readers: strip suspicious invisible Unicode, then rewrite prose while keeping facts, meaning, and the writer's voice. Use when the user asks to clean, humanize, polish, or finalize articles, manuscripts, reports, documentation, emails, product copy, UI…
oracle
Author an IMPL-BLIND spec-conformance oracle for an acceptance criterion the policy worklist (clad oracle --required) demands — an empty worklist means don't author unless the user explicitly asks. YOU spawn a blind sub-agent from a spec-only brief, then record it. Activate only when the connected project contains…
reviewer
Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad philosophical invariants. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized…
changelog
Render release notes / a changelog from the cladding spec. Use when the user asks for release notes, a changelog, 릴리즈 노트, 변경 이력, or "what changed (since )" — run clad changelog --json for the deterministic shipped-changes manifest, then write the human-facing notes FROM it, sourcing every claim from a feature title or…
doctor
Diagnose Cladding runtime health — Claude Code hook liveness and version, CI package pinning, lifecycle governance, and sentinel-miss frequency by phase × cause × fallback. Use when hooks may be silent, CI may float across Cladding releases, scan or run results look thinner than expected, or before tuning the host…