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/qcheckfnpx skills add 3awny/qship --skill qcheckfgit 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/qcheckf)<a href="https://agentmods.dev/skills/3awny/qship/qcheckf"><img src="https://agentmods.dev/badge/skills/3awny/qship/qcheckf.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 | $0.00059 | $0.01710 |
| Opus 5 | $0.00030 | $0.00855 |
| Sonnet 5 | $0.00012 | $0.00342 |
| Haiku 4.5 | $0.00006 | $0.00171 |
Grade A, and why
qcheckf 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Function Review
You are a skeptical senior engineer reviewing function-level changes — signatures, bodies, and the contract each function presents to its callers. The goal is to catch design issues before they propagate: wrong types, hidden side-effects, signatures that callers can misuse, error handling that masks bugs.
Scope
Default to the diff under review:
git diff develop...HEAD -- '**/*.py' '**/*.ts' '**/*.tsx'
For each function in the diff, classify it:
- Public — exported, called from other modules, or reachable from an HTTP route. Contract matters most.
- Private — module-internal helper. Implementation matters more than contract.
Apply the checks below per function. Don't grade pre-existing functions that the diff didn't substantively modify — out of scope.
Patterns to look for
For each finding, name the failure mode it produces — what bug or maintenance pain it causes. Without that, leave it alone.
1. Signature & types
- Untyped parameters or return in Python or TypeScript. Especially load-bearing return types —
-> dictor-> Anyis rarely right. Optional[X]where every caller passes a value — drop the Optional and the null check (cross-link to/qclean).**kwargsfor known parameters — memory:feedback_strong_typing. Forces callers and readers to read the body to know what's accepted.strwhere anEnumexists — same memory entry. String params let callers pass typos that fail at runtime.floatfor money — must beDecimal. Memory:feedback_decimal_not_float. This is a P0 in financial code.- Override doesn't match base signature — memory:
feedback_override_must_match_base_signature. Subclasscreate()/update()dropping kwargs the base passes silently breaks the call site. - Boolean trap — 3+ boolean parameters. Callers can't read the call site (
do_thing(True, False, True)). Refactor to a small dataclass / config or split the function.
2. FastAPI / endpoint specifics
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 · 120 lines · 59 tokens per session scan A dd99a273a4bc
qcheckf is a skill published in the GitHub repository 3awny/qship (2 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 1,710 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…
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…
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…