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/blendsdk/claude-codeops/clean_jsdocgit clone --depth 1 https://github.com/blendsdk/claude-codeopsWhat 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 | $0.00213 | $0.02139 |
| Opus 5 | $0.00106 | $0.01069 |
| Sonnet 5 | $0.00043 | $0.00428 |
| Haiku 4.5 | $0.00021 | $0.00214 |
Grade A, and why
clean_jsdoc 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 yesterday.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
clean_jsdoc — bring an existing codebase up to the CodeOps documentation standard
Retrofit the doc comments and code comments of an existing project so they obey the CodeOps
documentation standard (standards/coding-standards-full.md → Documentation). This is a one-time
(or occasional) cleanup: once a project is clean, the exec_plan skill keeps newly-written code
compliant, so you should rarely need to run this twice on the same tree.
Target root is $ARGUMENTS (first non-flag token) if given, else the current working directory.
Model note. This is high-volume, low-subtlety work: the detection is a deterministic grep and the rewrites are localized. Run it on a cheaper model (Sonnet, or Haiku for bulk) — the detection-first design keeps token cost proportional to the number of violations, not to the size of the codebase.
The standard being enforced (the five rules)
These come straight from standards/coding-standards-full.md; do not restate or reinvent them:
- Document every non-trivial entity — classes, methods, functions, exported globals — with a
doc comment (purpose, params, return, side effects) in the language's native format (JSDoc,
docstrings,
///, …). Public / exported / external-facing API is always documented; a genuinely self-evident one-liner may be left alone rather than padded with ceremony. - Comment code above a junior developer's level — non-obvious algorithms, invariants, subtle ordering / lifecycle dependencies, and "why it is done this way" decisions get a short comment so a junior can follow along. Trivial lines get nothing.
@exampleon public / external-facing API wherever practical — a worked, copy-pasteable example, because AI tools and human callers both learn the contract from it.- Calm, explaining tone — comments and doc comments read like a patient explanation, not terse cryptic notes. Explain why, not what.
- No change history in doc comments — no "fixed in vX", bug-fix notes, or maintainer traceability. A doc comment describes what the entity is and does now; the history belongs in the commit / PR body.
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.
- yesterday First seen · 132 lines · 0 tokens per session scan A cda1ece0a3f8
clean_jsdoc is a command published in the GitHub repository blendsdk/claude-codeops (4 stars, last pushed 1mo ago), licensed MIT. It adds 213 tokens to every session and 2,139 once invoked, about $0.0011 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.