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/whchoi98/project-init/add-modulegit clone --depth 1 https://github.com/whchoi98/project-initWhat 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 | $0.00482 |
| Opus 5 | $0.00007 | $0.00241 |
| Sonnet 5 | $0.00003 | $0.00096 |
| Haiku 4.5 | $0.00001 | $0.00048 |
Grade A, and why
add-module 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.
What it actually says
Add Module
Create a new module directory with documentation and update project-level docs.
Step 1: Validate Module Path
Target: $ARGUMENTS
- If no path provided, ask the user for the module path
- Verify the path is under a source directory (src/, app/, lib/, etc.)
- If the directory already exists, check if CLAUDE.md is missing and offer to create it
ls -la <module_path> 2>/dev/null
Step 2: Understand the Module
Ask the user:
- What is this module's responsibility? (one sentence)
- What are its key dependencies or relationships with other modules?
If the user skips, infer from the directory name.
Step 3: Create Module Directory and CLAUDE.md
mkdir -p <module_path>
Create <module_path>/CLAUDE.md with:
# <Module Name> Module
## Role
<module responsibility from user input>
## Key Files
<!-- Key files will be added as the module grows -->
## Dependencies
<relationships with other modules>
## Rules
<!-- Module-specific conventions -->
Step 4: Update docs/architecture.md
Read docs/architecture.md and add the new module to the Components section.
If a Data Flow section exists, suggest where the new module fits.
Step 5: Update Root CLAUDE.md
Read the root CLAUDE.md and update the Project Structure section to include the new module.
Step 6: Verify Hook Coverage
Read .claude/hooks/check-doc-sync.sh and verify the hook monitors the correct source directory path. If the new module is under a directory not covered by the hook, suggest updating it.
Step 7: Summary
Display:
- Created directory and CLAUDE.md
- Updated architecture.md
- Updated root CLAUDE.md
- Any suggested follow-up actions (e.g. create an ADR if this is a significant architectural addition)
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 · 76 lines · 14 tokens per session scan A cf8385faac53
add-module is a command published in the GitHub repository whchoi98/project-init (2 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 482 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 2026-08-31.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.