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 commands/caspian-sun/claude-code-workflow/prd-checkgit clone --depth 1 https://github.com/Caspian-Sun/claude-code-workflowWhat 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 | $0.00000 | $0.01934 |
| Opus 5 | $0.00000 | $0.00967 |
| Sonnet 5 | $0.00000 | $0.00387 |
| Haiku 4.5 | $0.00000 | $0.00193 |
Grade A, and why
prd-check 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 3d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are now a PRD completeness checker. Run hard-gate checks against the input PRD file and output whether it can proceed to the /plan task breakdown phase.
Applicable Scenarios
- User self-checks during PRD review — make a change and run immediately to know how far from "ready to run
/plan" - Mandatory pre-check for
/plan—/planmust run this command first; if it fails, task breakdown is refused
Input
@docs/prds/xxx.mdpath → read directly- No path → stop and ask: "Please specify the PRD file path, e.g.: /prd-check @docs/prds/login.md"
Checks (run in order, no short-circuit — report all issues at once)
Run all 5 checks in sequence, collect all results before summarizing. Do not stop at the first failure — users want to see all issues at once.
Check 1: Zero [TBD] hits (P0, must pass)
Full-text grep for [TBD]; hit count must be 0.
- Why strict:
[TBD]will propagate all the way totask.businessRules→ source file@rules→ testit()assertions — everything downstream becomes wrong. Blocking at the entry point has the lowest cost. - On failure: list the line number and text snippet for each hit
Check 2: Zero [TBD] hits in body text (P1)
Full-text grep for [TBD]. Allowed in:
- Metadata table ("Owner" field)
- Change log table ("Changed by" column)
Not allowed anywhere else in the document body.
- Why the metadata exception: these fields are collaboration info and don't affect downstream generation
- On failure: list the out-of-bounds hit locations
Check 3: Business Rules section contains no placeholders (P0)
Scan all entries under ### Business Rules sections; each entry must not contain:
-
[TBD] -
TODO/FIXME/??? -
Empty entries (e.g.,
1.) -
Why strict:
businessRulesis the direct source for task breakdown and test generation — placeholders mean downstream assertions are unreliable -
On failure: identify which feature point and which rule contains the placeholder
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.
- 3d ago First seen · 188 lines · 0 tokens per session scan A fdfe2de29f5d
prd-check is a command published in the GitHub repository Caspian-Sun/claude-code-workflow (10 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,934 tokens. 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 commands, from other repositories
vibe-agents
Step 4 of the vibe-coding workflow: generate AGENTS.md + tool configs so the AI builder stays on track.
mass-line
用群众路线收集多源信息、整合反馈并返回验证。.
sync-linear
Sync current work with Linear ticket status.
ship
Deliver the increment. Then go live with a rollback you have run.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
generate-rules
Generate development rules and standards into RULES.md.