Borrowing it
Nothing to install: this file belongs to vscarpenter/gsd-task-manager. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vscarpenter/gsd-task-manager/main/.claude/commands/qcheck.mdgit clone --depth 1 https://github.com/vscarpenter/gsd-task-managerWrote 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/commands/vscarpenter/gsd-task-manager/qcheck)<a href="https://agentmods.dev/commands/vscarpenter/gsd-task-manager/qcheck"><img src="https://agentmods.dev/badge/commands/vscarpenter/gsd-task-manager/qcheck/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/commands/vscarpenter/gsd-task-manager/qcheck"><img src="https://agentmods.dev/badge/commands/vscarpenter/gsd-task-manager/qcheck.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 | $0.00019 | $0.00527 |
| Opus 5.5 | $0.00008 | $0.00211 |
| Sonnet 5.5 | $0.00004 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
qcheck 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 1mo 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.
What it actually says
Review all changed files in this session as a skeptical staff engineer for the gsd-taskmanager codebase. Apply the full coding-standards.md and CLAUDE.md rules.
Run git status and git diff first to see what has changed. Then evaluate each changed file against:
- Standards compliance — The limits in
coding-standards.mdPart 3 (functions ≤40 lines, files ~400 lines, ≤3 nesting levels, no magic numbers), descriptive naming. - Type safety — All function signatures typed, no
anywithout justification, Zod validation at boundaries (user input, import, MCP tool inputs). - TDD evidence — Were tests written first? Check git log if uncertain. Each new behavior should have a behavior-named test.
- Test quality — Positive AND negative cases. Coverage ≥80% for changed files. Independent tests (no shared mutable state). Mocks at boundaries, not deep.
- Error handling — Typed errors, no swallowed exceptions,
toast.error()from sonner instead ofwindow.alert(). - Project-specific gotchas:
- PocketBase:
client_updated_at(notupdated) in sort/filter,_superusersadmin endpoint, 100ms push throttle, batch lookups not N+1. - Schema:
.safeParse()(not.parse()) on user input paths; import uses.strip(), export uses.strict(). - Tests:
bun run test(notbun test);localStorage.removeItem(key)(notclear()). - UI:
toast.error()(notalert()); WCAG AA baseline fromCLAUDE.mdDesign Context.
- PocketBase:
- Security — Input validation, no committed secrets, parameterized queries, least privilege.
- Observability — Structured logging via
lib/logger.ts, noconsole.*in production paths, no PII in logs. - Exit checklist — Every box for the task's tier in
coding-standards.mdPart 7 "Tiered Exit Checklists".
Distinguish blocking issues from suggestions. Prefix non-blocking comments with nit: or suggestion:.
Do not rewrite the code. Return a structured list of findings, organized by file, with file:line — issue — fix.
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.
- 1mo ago Changed a1165311bfc4
- 2mo ago First seen · 26 lines · 19 tokens per session scan A 93614b7a0c62
qcheck is a command published in the GitHub repository vscarpenter/gsd-task-manager (40 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 527 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other commands, from other repositories
councilreview
You are a panel of 8 independent expert reviewers. Each expert analyzes the same diff but from their specialized perspective. Experts do not coordinate -- they review independently and may contradict each other. After all reviews, an Auto-Fix phase applies safe fixes for LOW/MEDIUM findings.
codexreview
You are a hostile code reviewer. Your job is to find bugs, vulnerabilities, and defects. Not to compliment code.
ultra-agents
Autonomous multi-round review + fix loop — no per-round approval.
reply_to_comment
Call the replytocomment MCP tool to add a threaded reply to an existing comment. Read the comment id and the reply text from $ARGUMENTS. Use this to respond to my feedback, or as the author/defender role in a review thread before I resolve it. If no id is given, ask me which comment to reply to.
resolve_comment
Call the resolvecomment MCP tool to mark a comment as resolved once the edit is made. Read the comment id and a one-line note from $ARGUMENTS. If no id is given, first call checkcomments, make the edit each one asks for, then resolve each with a short note. Resolved comments turn green in the workspace so I can review…
show_diff
Call the showdiff MCP tool to show me a side-by-side visual diff (it returns an image in the chat). If I passed a checkpoint sha in $ARGUMENTS, diff that checkpoint; otherwise show my current uncommitted changes.