cocoindex-code

A semantic code search skill that finds relevant code by meaning rather than requiring an exact file, class, or function name. It uses local vector embeddings and can work offline.

In plain words
What is it for?
Use it to find code for tasks such as rate limiting, authentication middleware, or error handling, then inspect the returned file locations.
Why use it?
It helps locate implementations in an unfamiliar codebase when you know what the code does but not what it is called.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/brain-bootstrap/claude-code-brain-bootstrap/cocoindex-code
Any agent
npx skills add brain-bootstrap/claude-code-brain-bootstrap --skill cocoindex-code
Clone the repo
git clone --depth 1 https://github.com/brain-bootstrap/claude-code-brain-bootstrap

Made for: Claude Code, Codex.

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 607 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00060 $0.00607
Opus 5 $0.00030 $0.00303
Sonnet 5 $0.00012 $0.00121
Haiku 4.5 $0.00006 $0.00061

Measured 2d ago against content hash 0b6d48aee687, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cocoindex-code 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 2d 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.

.claude/skills/cocoindex-code/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Finds code by meaning using local vector embeddings (no API key, works offline). Complement to codebase-memory-mcp (structural) — use both for complete discovery.

When to Use This vs Other Tools

Use cocoindex-code Use codebase-memory-mcp instead
"find code that handles rate limiting" "who calls rateLimit()?"
"locate authentication middleware" "what does AuthService import?"
"find all error handling patterns" "trace path from HTTP handler to DB"
Exploring unfamiliar codebase Tracing known functions
Fuzzy conceptual search Exact structural traversal
{
  "query": "string — natural language or code snippet",
  "limit": 5,
  "offset": 0,
  "refresh_index": true,
  "languages": ["python", "typescript"],
  "paths": ["src/auth/*"]
}

Result: Array of {file_path, language, content, start_line, end_line, score}.

After getting results: Use the Read tool on file_path at start_lineend_line for full context.

Performance Tips

  • Set refresh_index: false for consecutive searches in the same session (no code changes)
  • Use languages filter to scope search (faster for single-language queries)
  • Use paths filter to limit to a directory (triggers full scan — slower than language filter)
  • Default limit is 5. Increase to 10–20 for broad exploration.

Lifecycle Management

Index not built yet: ccc index — or handled automatically on first MCP search.

After major changes: Index auto-refreshes on each MCP search call (refresh_index=True default).

Check status: ccc status shows chunks and file counts.

Switch embedding model: Edit ~/.cocoindex_code/global_settings.yml, then ccc reset && ccc index. Warning: model switch requires full re-index — different vector dimensions are incompatible.

Supported Languages (29)

Python, JavaScript, TypeScript/TSX/JSX, Rust, Go, Java, C, C++, C#, SQL, Shell/Bash, Markdown, PHP, Lua, Ruby, Swift, Kotlin, Scala, R, HTML, CSS/SCSS, JSON, YAML/TOML, XML, Solidity, Pascal, Fortran, plain text.

Read the full file on GitHub · 66 lines

Changes

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.

  1. 2d ago First seen · 66 lines · 60 tokens per session scan A 0b6d48aee687

Subscribe to this mod's changes

cocoindex-code is a skill published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 607 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

implement

TRIGGER when: user asks to implement, fix, build, or work on something — whether from a docs/wip plan OR a standalone task (bug fix, GitHub issue, one-off change). Examples: "work on task 1", "fix this bug", "implement feature X from the issue". Provides structured execution with profile detection, dependency…

serpro69/claude-toolbox · 79 tokens

review-spec

Use after implementing tasks or mid-feature to verify code matches design docs and ensure they are in sync. Detects spec deviations, missing implementations, doc inconsistencies, and outdated docs in design and implementation documentation.

serpro69/claude-toolbox · 44 tokens

chain-of-verification

Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification. Use when complex questions require fact-checking, technical accuracy, or multi-step reasoning.

serpro69/claude-toolbox · 41 tokens

review-design

Review design, implementation, and task documents produced by design. Evaluates document quality, internal consistency, and technical soundness. Use after design completes and before starting implement.

serpro69/claude-toolbox · 37 tokens

review-code

Code review of current git changes with an expert senior-engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements. Use when performing code reviews.

serpro69/claude-toolbox · 37 tokens

dependency-handling

TRIGGER when: adding or upgrading any dependency — library, SDK, framework, API, IaC API version (K8s/Terraform/Helm), CRD, or container image. Use BEFORE writing the call. Forces context7/capy lookup instead of guessing.

serpro69/claude-toolbox · 60 tokens