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/initgit 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 | $0.00009 | $0.00699 |
| Opus 5 | $0.00005 | $0.00349 |
| Sonnet 5 | $0.00002 | $0.00140 |
| Haiku 4.5 | $0.00001 | $0.00070 |
Grade A, and why
init 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Standards Initialization
Set up the code-standards plugin for this project. Walk the user through configuration options interactively.
Setup Process
Step 1: Check Existing Configuration
Check if .claude/code-standards.local.md already exists:
test -f .claude/code-standards.local.md && echo "EXISTS" || echo "NEW"
If EXISTS, inform user and ask whether to reconfigure or keep existing settings.
Step 2: Gather Preferences
Use AskUserQuestion to ask the user about their preferences:
Question 1 - Languages:
- Ask: "Which languages should be checked?"
- Options: TypeScript/JavaScript, Python, Go, Java, Ruby, All common languages
- Allow multi-select
Question 2 - Active Analysis:
- Ask: "Enable proactive analysis after code edits?"
- Options: Yes (recommended), No
Question 3 - Thresholds:
- Ask: "Which threshold strictness level?"
- Options:
- Relaxed (larger files/functions allowed)
- Standard (recommended defaults)
- Strict (smaller limits, stricter complexity)
Question 4 - CLAUDE.md Integration:
- Ask: "Add code standards rules to CLAUDE.md?"
- Options: Yes (recommended), No
Step 3: Create Settings File
Create .claude/code-standards.local.md with YAML frontmatter based on user choices.
Relaxed thresholds:
thresholds:
file_loc: 600
function_loc: 80
complexity: 20
Standard thresholds:
thresholds:
file_loc: 400
function_loc: 50
complexity: 15
Strict thresholds:
thresholds:
file_loc: 250
function_loc: 30
complexity: 10
Step 4: Update CLAUDE.md (if requested)
If user wants CLAUDE.md integration, append a ## Code Standards section:
## Code Standards
This project uses the code-standards plugin for quality enforcement.
### Size Limits
- Files: Target [X] LOC, max [Y] LOC
- Functions: Target [A] LOC, max [B] LOC
- Complexity: Max cyclomatic complexity [N]
### Principles
Follow KISS, DRY, YAGNI, and SRP principles.
### Review Checklist
- [ ] File/function sizes within limits
- [ ] One responsibility per module
- [ ] No silent error handling
- [ ] Tests cover important behavior
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 · 113 lines · 9 tokens per session scan A 4c1ea0cbf44d
init is a command published in the GitHub repository hculap/better-code (2 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 699 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.