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/defendend/Claude-ast-index-searchWrote 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/defendend/claude-ast-index-search/initialize-web)<a href="https://agentmods.dev/commands/defendend/claude-ast-index-search/initialize-web"><img src="https://agentmods.dev/badge/commands/defendend/claude-ast-index-search/initialize-web.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.01109 |
| Opus 5 | $0.00009 | $0.00554 |
| Sonnet 5 | $0.00003 | $0.00222 |
| Haiku 4.5 | $0.00002 | $0.00111 |
Grade A, and why
initialize-web 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 8d 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.
This is a copy
86% identical to initialize-android — 59 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize ast-index for Web Project
This command sets up ast-index integration for TypeScript/JavaScript web projects (React, Vue, Svelte, Angular, NestJS, etc.).
Steps to Execute
1. Check Prerequisites
Verify ast-index is installed:
ast-index version
If not installed, inform user to run:
brew tap defendend/ast-index
brew install ast-index
2. Create/Update .claude/settings.json
First, ensure the directory exists:
mkdir -p .claude
Then create or merge into .claude/settings.json. If file doesn't exist, create it with this content:
{
"extraKnownMarketplaces": {
"ast-index": {
"source": {
"source": "github",
"repo": "defendend/Claude-ast-index-search"
}
}
},
"enabledPlugins": {
"ast-index@ast-index": true
},
"permissions": {
"allow": [
"Bash(ya tool ast-index *)",
"Bash(ast-index *)"
]
}
}
Important: If .claude/settings.json already exists, MERGE the keys (don't replace the whole file).
3. Create .claude/rules/ast-index.md (CRITICAL)
Create the rules directory and ast-index rules file:
mkdir -p .claude/rules
Create file .claude/rules/ast-index.md with this content:
# ast-index Rules
## Mandatory Search Rules
1. **ALWAYS use ast-index FIRST** for any code search task
2. **NEVER duplicate results** — if ast-index found usages/implementations, that IS the complete answer
3. **DO NOT run grep "for completeness"** after ast-index returns results
4. **Use grep/Search ONLY when:**
- ast-index returns empty results
- Searching for regex patterns (ast-index uses literal match)
- Searching for string literals inside code (`"some text"`)
- Searching in comments content
## Why ast-index
ast-index is 17-69x faster than grep (1-10ms vs 200ms-3s) and returns structured, accurate results.
## Command Reference
| Task | Command | Time |
|------|---------|------|
| Universal search | `ast-index search "query"` | ~10ms |
| Find class/component | `ast-index class "ComponentName"` | ~1ms |
| Find symbol | `ast-index symbol "SymbolName"` | ~1ms |
| Find usages | `ast-index usages "SymbolName"` | ~8ms |
| Find implementations | `ast-index implementations "Interface"` | ~5ms |
| Call hierarchy | `ast-index call-tree "function" --depth 3` | ~1s |
| Find callers | `ast-index callers "functionName"` | ~1s |
| Module deps | `ast-index deps "module-name"` | ~10ms |
| File outline | `ast-index outline "File.tsx"` | ~1ms |
## TypeScript/JavaScript-Specific Commands
| Task | Command |
|------|---------|
| Find React components | `ast-index class "Component"` |
| Find React hooks | `ast-index search "use" --kind function` |
| Find decorators | `ast-index search "@Controller"` |
| Find interfaces | `ast-index class "Props"` |
| Find types | `ast-index symbol "DTO"` |
## Index Management
- `ast-index rebuild` — Full reindex (run once after clone)
- `ast-index update` — After git pull/merge
- `ast-index stats` — Show index statistics
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.
- 8d ago First seen · 175 lines · 17 tokens per session scan A e2a3cebadc7b
initialize-web is a command published in the GitHub repository defendend/Claude-ast-index-search (557 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 1,109 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to initialize-android, differing in 59 lines, and is treated as a copy.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.