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.
git clone --depth 1 https://github.com/hculap/better-codeWrote 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/hculap/better-code/generate)<a href="https://agentmods.dev/commands/hculap/better-code/generate"><img src="https://agentmods.dev/badge/commands/hculap/better-code/generate/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/hculap/better-code/generate"><img src="https://agentmods.dev/badge/commands/hculap/better-code/generate.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 | $0.00007 | $0.01779 |
| Opus 5.5 | $0.00003 | $0.00712 |
| Sonnet 5.5 | $0.00001 | $0.00356 |
| Haiku 4.5 | $0.00001 | $0.00178 |
Grade A, and why
generate 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 1mo 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Generator
Generate documentation for a specific feature, component, or module using the appropriate specialized agent.
Arguments
-
feature(required): What to document- Feature name: "user authentication", "payment processing"
- Component path: "./src/components/Button"
- Module: "api/users"
-
--type(optional): Document type to generatetutorial: Learning-oriented walkthroughhowto: Task-oriented guidereference: Technical reference documentationexplanation: Conceptual explanation- If omitted: Generate appropriate type based on context
-
--output(optional): Output path for generated documentation- Default: Suggests appropriate location based on project structure
Process
Step 1: Load Configuration
Read .claude/doc-master.local.md for:
- Documentation standard (Diátaxis/Traditional/Custom)
- Custom rules (if applicable)
- Project-specific notes
Step 2: Analyze Feature
-
Locate feature code:
- Search for related files
- Read main implementation
- Identify dependencies
-
Understand feature:
- What does it do?
- How is it used?
- What are the public interfaces?
- What are common use cases?
-
Identify domain:
- Backend → Use backend-docs agent
- Frontend → Use frontend-docs agent
- API → Use api-docs agent
- Database → Use database-docs agent
- Architecture → Use architecture-docs agent
- Tests → Use test-docs agent
- User-facing → Use user-guide-docs agent
- Compliance → Use compliance-docs agent
- Mobile → Use mobile-docs agent
Step 3: Determine Document Type
If --type not specified, determine based on:
- Feature nature (new feature → tutorial, existing API → reference)
- User needs (ask if unclear)
- Existing documentation gaps
Step 4: Gather Information
Collect all information needed for documentation:
- Code signatures, parameters, return types
- Usage examples from tests or existing code
- Related documentation
- Error cases and edge cases
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.
- 1mo ago First seen · 290 lines · 7 tokens per session scan A d2af2c0b0504
generate is a command published in the GitHub repository hculap/better-code (2 stars, last pushed 7d ago), licensed MIT. It adds 7 tokens to every session and 1,779 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 2026-08-31.
Other commands, from other repositories
sync-config
Sync a scraping config's URLs against the live documentation site.
sm-buff
You usually don't run buff directly — run sm sail. sm sail drives the whole PR to green and calls buff watch / triage for you, stopping only when it needs you to act (see /sm-sail). Reach for sm buff here only for surgical work: inspecting a specific failure, or resolving a single review thread when sail has parked on…
sm-swab
Run slop-mop's iterative development loop for this repository.
ccg-latent
Latent Chain Mode for structured, token-efficient reasoning with hidden-state management.
latent-fix
Quick fix cho file đang mở hoặc file được chỉ định. Tối đa 1-2 patches.
latent-status
Quick status check cho Latent Chain Mode và current workflow.