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-compoundgit 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 | $0.00014 | $0.01676 |
| Opus 5 | $0.00007 | $0.00838 |
| Sonnet 5 | $0.00003 | $0.00335 |
| Haiku 4.5 | $0.00001 | $0.00168 |
Grade A, and why
writing:compound scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Compound Command
Turn this piece's successes into permanent improvements for future writing.
Input
<piece_path> #$ARGUMENTS </piece_path>
If "latest" is provided, find the most recent published/approved piece.
The Compound Philosophy
Each piece of writing should make the next piece easier to write.
This command extracts what worked and encodes it for reuse:
- Hook formulas that grabbed attention
- Structure patterns that flowed well
- Voice elements that landed
- Transitions that felt invisible
Workflow Overview
- Analyze what made this piece work
- Extract reusable patterns
- Update style documentation
- Create templates for similar pieces
- Log anti-patterns that were edited out
Phase 1: Success Analysis
Load the Piece and History
Read the final published version
Read all draft versions (v1, v2, etc.)
Read review reports
Identify:
- What changed between drafts
- What reviewers praised
- What the writer kept unchanged
Identify What Worked
Use AskUserQuestion:
What made this piece successful?
1. The hook grabbed attention
2. The structure was clear
3. The voice was consistent
4. The examples were concrete
5. Something else: [describe]
Allow multiple selections to understand success factors.
Phase 2: Extract Patterns
Hook Analysis
## Hook Extraction
**Opening text**:
> [First 50-100 words]
**Hook type**: [Story/Stat/Tension/Question/Surprise]
**Why it worked**:
- [Specific reason 1]
- [Specific reason 2]
**Formula abstracted**:
[General pattern that could be reused]
**Similar topics it could work for**:
- [Topic 1]
- [Topic 2]
Structure Analysis
## Structure Extraction
**Pattern used**: [Problem-Solution/Journey/Listicle/Story]
**Section breakdown**:
1. [Section type] - [purpose] - [word count]
2. [Section type] - [purpose] - [word count]
...
**What made this structure work**:
- [Insight 1]
- [Insight 2]
**Topics this structure fits**:
- [Topic type 1]
- [Topic type 2]
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 · 323 lines · 14 tokens per session scan A 8623d175a4c8
writing:compound is a command published in the GitHub repository robertguss/claude-code-toolkit (108 stars, last pushed 24d ago), licensed MIT. It adds 14 tokens to every session and 1,676 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.