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/hculap/better-code/plangit clone --depth 1 https://github.com/hculap/better-codeWhat 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 | $0.00007 | $0.01313 |
| Opus 5 | $0.00003 | $0.00656 |
| Sonnet 5 | $0.00001 | $0.00263 |
| Haiku 4.5 | $0.00001 | $0.00131 |
Grade A, and why
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 yesterday.
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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Plan Generator
Create a structured documentation plan for a project, feature, or component.
Arguments
scope(optional): What to plan documentation for- If omitted: Plan for entire project
- Feature name: Plan for specific feature (e.g., "user authentication")
- Path: Plan for specific directory (e.g., "./src/api")
Process
Step 1: Load Configuration
Read .claude/doc-master.local.md to determine documentation standard.
Default to Diátaxis if not configured.
Step 2: Analyze Scope
For entire project:
- Scan codebase structure
- Identify major components/modules
- Check existing documentation
- Map what needs documenting
For specific feature:
- Locate feature code
- Understand feature scope
- Identify related components
- Determine documentation needs
For specific path:
- Analyze code in directory
- Identify public interfaces
- Determine documentation requirements
Step 3: Identify Target Audiences
Ask user (if not clear from context):
- Who will read this documentation?
- Developers using the API
- End users of the product
- Internal team members
- Operations/DevOps
- All of the above
Step 4: Gap Analysis
Compare existing documentation against needs:
- What exists and is current?
- What exists but needs updating?
- What's completely missing?
- What should be removed (outdated)?
Step 5: Generate Plan
Create documentation plan based on configured standard:
Diátaxis Plan Structure:
# Documentation Plan: [Scope]
## Overview
- Target audience: [audiences]
- Documentation standard: Diátaxis
- Estimated documents: [count]
## Tutorials (Learning-Oriented)
Priority documents to create:
### 1. Getting Started Tutorial
- **Purpose**: First-time user onboarding
- **Covers**: Installation, basic setup, first use
- **Estimated length**: 1,000-1,500 words
- **Prerequisites**: None
### 2. [Feature] Tutorial
- **Purpose**: Learn [feature] through building
- **Covers**: [topics]
- **Estimated length**: [words]
- **Prerequisites**: Getting Started
## How-To Guides (Task-Oriented)
Priority guides to create:
### 1. How to [Task]
- **Purpose**: Solve specific problem
- **Covers**: [steps]
- **Estimated length**: 500-800 words
[Additional guides...]
## Explanations (Understanding-Oriented)
Conceptual documents needed:
### 1. Architecture Overview
- **Purpose**: Explain system design
- **Covers**: Components, data flow, decisions
- **Estimated length**: 1,500-2,000 words
[Additional explanations...]
## Reference (Information-Oriented)
Reference documentation needed:
### 1. API Reference
- **Purpose**: Complete API documentation
- **Covers**: All public endpoints/methods
- **Format**: Structured reference
[Additional references...]
## Existing Documentation Status
| Document | Status | Action |
|----------|--------|--------|
| README.md | Outdated | Update |
| api.md | Missing | Create |
| setup.md | Current | Keep |
## Recommended Order
1. [First priority document]
2. [Second priority document]
...
## Timeline Suggestion
- Phase 1: Core documents (README, Getting Started)
- Phase 2: API Reference
- Phase 3: How-to guides
- Phase 4: Explanations and tutorials
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.
- yesterday First seen · 244 lines · 7 tokens per session scan A 6e53311ba590
plan is a command published in the GitHub repository hculap/better-code (2 stars, last pushed 7mo ago), licensed MIT. It adds 7 tokens to every session and 1,313 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
create-skill
Create an AI skill from any source (URL, repo, PDF, video, notebook, etc.).
sync-config
Sync a scraping config's URLs against the live documentation site.
create_plan
Create detailed implementation plans through interactive research and iteration.
review-pr
Multi-agent PR review with four modes (review, re-review, self-review, address-feedback) - spawns parallel subagents, saves diff to /tmp for context efficiency, supports file exclusion patterns.
research_codebase
Document codebase as-is with thoughts directory for historical context.
iterate_plan
Iterate on existing implementation plans with thorough research and updates.