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/robertguss/claude-code-toolkit/writing-reviewgit clone --depth 1 https://github.com/robertguss/claude-code-toolkitWrote 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/robertguss/claude-code-toolkit/writing-review)<a href="https://agentmods.dev/commands/robertguss/claude-code-toolkit/writing-review"><img src="https://agentmods.dev/badge/commands/robertguss/claude-code-toolkit/writing-review.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 | $0.00013 | $0.01297 |
| Opus 5 | $0.00006 | $0.00648 |
| Sonnet 5 | $0.00003 | $0.00259 |
| Haiku 4.5 | $0.00001 | $0.00130 |
Grade A, and why
writing:review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Review Command
Multi-agent editorial review that examines content from every angle.
Input
<draft_path> #$ARGUMENTS </draft_path>
If "latest" is provided, find the most recent draft in drafts/.
Workflow Overview
This command executes the review phase:
- Load draft and context
- Launch parallel review agents
- Collect and prioritize findings
- Present interactive triage
- Apply accepted fixes
Phase 1: Load Context
Read Draft
Read the draft file
Extract:
- Title and metadata
- Word count
- Style used
- Voice profile (if any)
Load Review Context
If voice profile exists: Load for voice-guardian
If style guide specified: Load rules
Find sources.md for fact-checking
Phase 2: Parallel Review Agents
Launch ALL relevant agents simultaneously:
Core Reviews (Always Run)
Task voice-guardian: "Check voice consistency in this draft.
Voice profile: [profile or 'infer from content']
Draft: [draft content]
Return: Voice score, drift areas, specific fixes."
Task clarity-editor: "Review for clarity, concision, jargon, and passive voice.
Draft: [draft content]
Return: Prioritized issues with before/after fixes."
Task fact-checker: "Verify all claims against sources.
Draft: [draft content]
Sources: [sources.md content]
Return: Claim verification report."
Task structure-architect: "Analyze flow and structure.
Draft: [draft content]
Return: Flow analysis, gap identification, structure assessment."
Style Reviews (Based on Context)
If using Every style:
Task every-style-editor: "Check against Every's style guide.
Draft: [draft content]
Return: Style violations with line numbers and fixes."
If technical content:
Skill: pragmatic-writing
Apply pragmatic writing principles and report issues.
If opinion/persuasive content:
Skill: dhh-writing
Apply DHH's direct, opinionated style checks.
Publishing Reviews (If Requested)
Task publishing-optimizer: "Analyze for SEO and social potential.
Draft: [draft content]
Return: SEO recommendations, social hooks, headline alternatives."
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 · 259 lines · 13 tokens per session scan A 76eada5dc1e1
writing:review is a command published in the GitHub repository robertguss/claude-code-toolkit (108 stars, last pushed 26d ago), licensed MIT. It adds 13 tokens to every session and 1,297 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
skillkit
Research-driven toolkit for creating and validating skills and subagents with structured workflows, gates, and automation scripts.
validate-plan
Validate implementation plans against DRY, YAGNI, TDD principles before execution.
verify
Enforce 7 production safety gates with evidence before deployment.
commit
Analyze Git changes and generate a conventional commit message following the Commitizen format.
README
Git workflow and quality assurance commands for the claude-skills repository.
medical-necessity
Generate medical necessity letters citing chiropractic clinical guidelines for insurance authorization and appeals.