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-plangit clone --depth 1 https://github.com/robertguss/claude-code-toolkitWhat 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 | $0.00015 | $0.01119 |
| Opus 5 | $0.00008 | $0.00560 |
| Sonnet 5 | $0.00003 | $0.00224 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade A, and why
writing:plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Plan Command
Transform a topic or brief into a comprehensive research package and structured outline.
Input
#$ARGUMENTS
Workflow Overview
This command executes the research and planning phase of the writing workflow:
- Clarify the brief (what, who, why)
- Parallel research (sources, audience, competitors)
- Two-gate assessment (material sufficiency, message clarity)
- Create structured outline with hooks
Phase 1: Clarify the Brief
Before any research, answer these questions:
The Core Questions
- What's the argument? - The specific point to make (not just the topic)
- Who's the reader? - Specific audience, not "everyone"
- What should they do after? - The call to action
Brief Clarification
If the input is vague, use AskUserQuestion to clarify:
Questions to ask:
- "What's the specific angle or argument? (Not just the topic, but your take)"
- "Who specifically are you writing for?"
- "What should readers do after reading?"
- "What channel? (blog, newsletter, social, documentation)"
- "Target length? (short: <1000 words, medium: 1000-2500, long: 2500+)"
Only proceed when you have clear answers.
Phase 2: Parallel Research
Launch three research agents simultaneously:
Task source-researcher: "Research sources for: [topic]
Find:
- Primary sources (original research, data)
- Expert perspectives
- Supporting statistics
- Concrete examples
Return structured source list with quotes and reliability ratings."
Task source-researcher: "Analyze the target audience for: [topic]
Determine:
- What they already know
- Their emotional state
- Their goals and objections
- The action they should take
Return audience profile."
Task source-researcher: "Analyze competitor content for: [topic]
Find:
- Top existing pieces on this topic
- Their angles and approaches
- Gaps and weaknesses
- Differentiation opportunities
Return competitive analysis."
Phase 3: Two-Gate Assessment
Gate 1: Material Sufficiency
Ask: "Could I write this without inventing facts?"
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.
- 2d ago First seen · 178 lines · 15 tokens per session scan A 3def09e6eb12
writing:plan is a command published in the GitHub repository robertguss/claude-code-toolkit (108 stars, last pushed 24d ago), licensed MIT. It adds 15 tokens to every session and 1,119 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.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.