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 skills/bidiche49/claude-conf/code-index-bootstrapnpx skills add Bidiche49/claude-conf --skill code-index-bootstrapgit clone --depth 1 https://github.com/Bidiche49/claude-confWrote 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/skills/bidiche49/claude-conf/code-index-bootstrap)<a href="https://agentmods.dev/skills/bidiche49/claude-conf/code-index-bootstrap"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/code-index-bootstrap.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 | $0.00072 | $0.03125 |
| Opus 5 | $0.00036 | $0.01563 |
| Sonnet 5 | $0.00014 | $0.00625 |
| Haiku 4.5 | $0.00007 | $0.00313 |
Grade A, and why
code-index-bootstrap 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 3d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/code-index-bootstrap
You are setting up code-index (claude-conf module) inside the user's current project. Your goal: install the right indexer + git hooks so docs/.code-map/ regenerates automatically on every commit, with measured token economy ≥ 50% vs reading the source directly.
Mission
- Detect the project stack by scanning marker files in the project root.
- If a native stack setup exists under
~/.claude/code-index/stacks/<stack>/_setup.sh→ delegate to it (fast path). - Otherwise → enter generation mode with the 4 non-negotiable guardrails defined below.
- Always end with auto-validation: parse 5 source samples, confirm format conformance, measure token economy.
Step 1 — Detect stack
Run ls -la in the project root and check, in this order:
| Marker | Stack |
|---|---|
pubspec.yaml |
dart |
package.json |
js (TypeScript inferred via tsconfig.json or .ts files) |
go.mod |
go |
Cargo.toml |
rust |
pyproject.toml / requirements.txt / setup.py |
python |
If multiple markers are present (e.g. monorepo with both Go and JS), ask the user which stack to index. Do not guess.
If none match, tell the user the project layout is unsupported and stop. Do not invent.
Step 2 — Dispatch or generate
Check if a native installer exists:
ls ~/.claude/code-index/stacks/<detected-stack>/_setup.sh
Case A — native installer present (Dart in v0.1)
Run it directly. Pass --source and --out only if the user requested non-default values.
bash ~/.claude/code-index/stacks/<stack>/_setup.sh
The script handles everything (copy indexer, install hooks, patch .gitignore, configure git core.hooksPath, run first index). Then jump to Step 4 (validation).
Case B — generation mode
Only enter this branch if no native installer exists for the detected stack. Then all 4 guardrails below are mandatory.
The 4 guardrails (non-negotiable in generation mode)
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.
- 3d ago First seen · 269 lines · 72 tokens per session scan A 68cf293ff569
code-index-bootstrap is a skill published in the GitHub repository Bidiche49/claude-conf (2 stars, last pushed 4mo ago), licensed MIT. It adds 72 tokens to every session and 3,125 once invoked, about $0.0004 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 skills, from other repositories
hooks-eval
Evaluate hook security, performance, and SDK compliance. Use for audits.
webmcp-setup
Bootstraps webmcp-react into an existing React or Next.js app. Installs dependencies, adds WebMCPProvider, creates a first tool, and configures the MCP client bridge. Use when the user wants to set up WebMCP, add MCP tools to their app, integrate webmcp-react, or make their React app accessible to AI agents.
goal
Run a large or unfamiliar goal through the full ballast pipeline — mobilize what you already hold, terrain scan, full skeleton, atomic foundation learning with verification, then build from bedrock to a verified done. Use when the user hands over a big goal, enters a new field, or asks to learn X in order to achieve Y.
report
Read the delivery log and say which rules actually fire, which never have, and what to prune or fix. Use when the user asks whether ballast is doing anything, wants to clean up their rule catalog, or on a periodic review.
engram
Claude Engram persistent memory — quick reference for all MCP tools and automatic hook behaviors. Use when you need to remember how to store, search, or manage memories, or query session history.
eval-harness
Assessment-driven development — Quantify code generation quality with pass@k / pass^k metrics, automatically scored by Grader.