Borrowing it
Nothing to install: this file belongs to Lanzelot1/claw-brain. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Lanzelot1/claw-brain/main/.claude/commands/synthesize.mdgit clone --depth 1 https://github.com/Lanzelot1/claw-brainWrote 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/lanzelot1/claw-brain/synthesize)<a href="https://agentmods.dev/commands/lanzelot1/claw-brain/synthesize"><img src="https://agentmods.dev/badge/commands/lanzelot1/claw-brain/synthesize/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/lanzelot1/claw-brain/synthesize"><img src="https://agentmods.dev/badge/commands/lanzelot1/claw-brain/synthesize.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00012 | $0.00656 |
| Opus 5.5 | $0.00005 | $0.00262 |
| Sonnet 5.5 | $0.00002 | $0.00131 |
| Haiku 4.5 | $0.00001 | $0.00066 |
Grade A, and why
synthesize 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 2mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create or update synthesized wiki pages (entity pages, concept pages, or comparison pages) from existing knowledge source files.
Arguments
Optional: specific topic, entity, or concept name. E.g. /synthesize "machine learning" or /synthesize "Company X vs Company Y"
Steps
- Read
memory/_index.mdto understand all available knowledge - Determine what to synthesize:
- If an argument was given: focus on that topic/entity/concept
- If no argument: scan knowledge files to suggest candidates. Look for:
- Entities (people, companies, products, tools) mentioned in 3+ source files
- Concepts that span multiple areas
- Topics where information is scattered across files
- Present candidates and ask: "Which would you like me to synthesize?"
- Gather source material: Read all relevant source files (
type: sourceor no type field). Note the specific facts, data, and quotes from each. - Check for existing wiki page: Search
knowledge/for an existing wiki page on this topic (type: wikiin frontmatter). - Create or update the wiki page:
- Location:
knowledge/{most-relevant-area}/orknowledge/wiki/if cross-cutting - Frontmatter:
--- type: wiki source: "synthesized from knowledge sources" created: YYYY-MM-DD updated: YYYY-MM-DD --- - Content: Weave together facts from the source files into a coherent page. Use specific facts, data, and quotes — not vague summaries. Organize with clear headings.
- If sources contradict: Note the contradiction explicitly rather than silently picking one.
- Required
## Sourcessection at the bottom: list every source file used, with markdown links and a brief note on what each contributed. - Cross-references: Add
## Relatedsection linking to related wiki pages and source files.
- Location:
- Update index: Add the wiki page to the "Wiki Pages" section in
memory/_index.md - Update source files: In each source file that was used, add a cross-reference back to the new wiki page (in their
## Relatedsection). - Log: Append to
memory/log.md:YYYY-MM-DD HH:MM | synthesize | created/updated {wiki-page-path} from {N} sources
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.
- 2mo ago First seen · 54 lines · 12 tokens per session scan A c2d03125f56b
synthesize is a command published in the GitHub repository Lanzelot1/claw-brain (11 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 656 once invoked, about $0.0000 per session on Opus 5.5. 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
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.
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.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.