Agent skill

ccc Semantic Code Search

by cocoindex-io in cocoindex-io/cocoindex-code

Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path.

Apache-2.0Auto-check passedAgent Workflows

Install ccc Semantic Code Search

skills CLI
$ npx skills add cocoindex-io/cocoindex-code --skill ccc -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cocoindex-io/cocoindex-code ccc --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cocoindex-io/cocoindex-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ccc .claude/skills/ccc && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ccc
GitHub stars
2.7k
Token cost
~938 tokens
SKILL.md length
436 words
Files
3 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
Apache-2.0

At a glance

Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path.

  • Finding code by concept, such as where retries or authentication are handled
  • SKILL.md covers Ownership, Searching the Codebase, Settings and Management & Troubleshooting
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Refreshing the codebase index after refactors or new files

What it does

ccc is the command line for CocoIndex Code, giving the agent semantic search over the current codebase plus index management. The agent owns the whole lifecycle, so it does not ask you to run steps. If a search or index command fails because the project is not initialized, it runs `ccc init` from the project root, then `ccc index`, and retries. It refreshes the index at the start of a session or after significant changes such as new files, refactors or renamed modules, but not between consecutive searches when no code changed.

Queries should describe a concept, function or behavior rather than exact syntax, for example database connection pooling or error handling retry logic. Results can be limited by language with repeated `--lang` flags, by a glob with `--path` (the default is the current directory), and paged with `--offset` and `--limit`. The agent never runs `ccc init` in the settings directory, usually your home folder, and leaves `ccc reset` to you. Installation, management and settings details are in two reference files; the excerpt is cut off after pagination.

When your agent uses it

  • Finding code by concept, such as where retries or authentication are handled
  • Refreshing the codebase index after refactors or new files
  • Searching only certain languages or subdirectories

Example prompts

  • “Find where we handle database connection pooling.”
  • “Update the index and search for the user authentication flow under src/api.”
  • “Search only the Python and Markdown files for the database schema.”

Requirements

  • The ccc CLI (CocoIndex Code), installed as described in references/management.md

What it can do on your machine

Read from SKILL.md and the folder at commit b883be0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

ccc Semantic Code Search loads about 938 tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 436 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~88
When it runs · the whole SKILL.md, loaded when a task matches
~938
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cocoindex-io/cocoindex-code at commit b883be0, republished under its Apache-2.0 licence (© cocoindex-io). 436 words, ~938 tokens.

Download SKILL.mdSave it as .claude/skills/ccc/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
ccc
description
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the index', 'ccc', 'cocoindex-code'.

ccc - Semantic Code Search & Indexing

ccc is the CLI for CocoIndex Code, providing semantic search over the current codebase and index management.

Ownership

The agent owns the ccc lifecycle for the current project — initialization, indexing, and searching. Do not ask the user to perform these steps; handle them automatically.

  • Initialization: If ccc search or ccc index fails with an initialization error (e.g., "Not in an initialized project directory"), run ccc init from the project root directory, then ccc index to build the index, then retry the original command.
    • Exception: if ccc index refuses because the directory holds ccc's user settings directory (usually your home directory), do not run ccc init there. Run ccc from inside the project instead, or ask the user which project to use.
    • Exception: if a ccc note says the project in use is that directory (a repo below it has no project of its own), tell the user. Do not run ccc reset there yourself: whether it should stay a project is the user's call.
  • Index freshness: Keep the index up to date by running ccc index (or ccc search --refresh) when the index may be stale — e.g., at the start of a session, or after making significant code changes (new files, refactors, renamed modules). There is no need to re-index between consecutive searches if no code was changed in between.
  • Installation: If ccc itself is not found (command not found), refer to management.md for installation instructions and inform the user.

Searching the Codebase

To perform a semantic search:

bash
ccc search <query terms>

The query should describe the concept, functionality, or behavior to find, not exact code syntax. For example:

bash
ccc search database connection pooling
ccc search user authentication flow
ccc search error handling retry logic
Show full SKILL.md (182 more words)Show less
Filtering Results
  • By language (--lang, repeatable): restrict results to specific languages.

    bash
    ccc search --lang python --lang markdown database schema
  • By path (--path): restrict results to a glob pattern relative to project root. If omitted, defaults to the current working directory (only results under that subdirectory are returned).

    bash
    ccc search --path 'src/api/*' request validation
Pagination

Results default to the first page. To retrieve additional results:

bash
ccc search --offset 5 --limit 5 database schema

If all returned results look relevant, use --offset to fetch the next page — there are likely more useful matches beyond the first page.

Working with Search Results

Search results include file paths and line ranges. To explore a result in more detail:

  • Use the editor's built-in file reading capabilities (e.g., the Read tool) to load the matched file and read lines around the returned range for full context.
  • When working in a terminal without a file-reading tool, use sed -n '<start>,<end>p' <file> to extract a specific line range.

Settings

To view or edit embedding model configuration, include/exclude patterns, or language overrides, see settings.md.

Management & Troubleshooting

For installation, initialization, daemon management, troubleshooting, and cleanup commands, see management.md.

© cocoindex-io, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/ccc of cocoindex-io/cocoindex-code.

  • SKILL.md
  • references/management.md
  • references/settings.md

Open the folder on GitHubat commit b883be0

Compare with similar skills

ccc Semantic Code Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

ccc Semantic Code Search compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
ccc Semantic Code Search this skillcocoindex-io/cocoindex-code2.7k—~938Automated safety check: PassApache-2.0
Repomix Codebase Packeryamadashy/repomix29k—~1.3kAutomated safety check: NotesMIT
Ripwire Codebase Orientationredhat-et/ripwire2.4k—~4.5kAutomated safety check: NotesApache-2.0
tilth Code Reading CLIjahala/tilth352—~1.1kAutomated safety check: PassMIT
Codebase Handbook BuilderRuhan-Wang/Harness_Handbook332—~2.2kAutomated safety check: PassApache-2.0
CodemapJordanCoin/codemap704—~1.8kAutomated safety check: PassMIT

Similar skills

  • Repomix Codebase Packer

    yamadashy/repomix

    Packs a local directory or remote GitHub repository into one AI-friendly file with Repomix, then searches it to explore structure, find patterns and count tokens.

    29k GitHub stars~1.3k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check: notes
  • Maps an unfamiliar repo or subsystem with the ripwire CLI before reading files, climbing an escalation ladder only until you are oriented.

    2.4k GitHub stars~4.5k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Replaces grep, cat, find and ls with the tilth CLI, which returns AST-aware outlines, definitions, usages and callers across many languages in one call.

    352 GitHub stars~1.1k tokensUpdated 11 days ago
    DevelopmentAuto-check passed
  • Codebase Handbook Builder

    Ruhan-Wang/Harness_Handbook

    Generates, refreshes, validates and uses a compact handbook that maps where a change touches in a repository, using the active Codex session and no external LLM API.

    332 GitHub stars~2.2k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Codemap

    JordanCoin/codemap

    Gives an agent a quick map of a codebase's structure, dependencies, changes and handoffs, and tunes per-project config so the output stays code-first.

    704 GitHub stars~1.8k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • MCP Code Search Tool Selection

    Context-Engine-AI/Context-Engine

    Rules for choosing Qdrant-Indexer semantic search over grep or file reads when exploring code, debugging or asking where and why questions.

    402 GitHub stars~1.3k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed

Questions about ccc Semantic Code Search

What does ccc Semantic Code Search do?

Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path. ccc is the command line for CocoIndex Code, giving the agent semantic search over the current codebase plus index management. The agent owns the whole lifecycle, so it does not ask you to run steps.

When should I use ccc Semantic Code Search?

ccc Semantic Code Search fits situations like: finding code by concept, such as where retries or authentication are handled; refreshing the codebase index after refactors or new files; searching only certain languages or subdirectories.

How do I install ccc Semantic Code Search in Claude Code?

Run `npx skills add cocoindex-io/cocoindex-code --skill ccc -a claude-code`. Or copy the skill folder (skills/ccc in cocoindex-io/cocoindex-code) into .claude/skills/ccc in your project. Claude Code loads it when a task matches its description.

How do I install ccc Semantic Code Search in Codex?

Run `npx skills add cocoindex-io/cocoindex-code --skill ccc -a codex`. Or copy the skill folder (skills/ccc in cocoindex-io/cocoindex-code) into .agents/skills/ccc in your project. Codex loads it when a task matches its description.

Can I use ccc Semantic Code Search in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cocoindex-io/cocoindex-code --skill ccc -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ccc, .gemini/skills/ccc, .github/skills/ccc and .opencode/skills/ccc in your project.

What does ccc Semantic Code Search need to run?

SKILL.md names no scripts, command-line tools or credentials: ccc Semantic Code Search is instructions for the agent only. Our summary lists: The ccc CLI (CocoIndex Code), installed as described in references/management.md.

Does ccc Semantic Code Search access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is ccc Semantic Code Search safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does ccc Semantic Code Search use?

ccc Semantic Code Search is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does ccc Semantic Code Search use?

About 938 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2k tokens, read only when the agent opens those files.

What are the alternatives to ccc Semantic Code Search?

Skills that share tags, products or a category with ccc Semantic Code Search: Repomix Codebase Packer (yamadashy/repomix, 29k stars), Ripwire Codebase Orientation (redhat-et/ripwire, 2.4k stars), tilth Code Reading CLI (jahala/tilth, 352 stars) and Codebase Handbook Builder (Ruhan-Wang/Harness_Handbook, 332 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains ccc Semantic Code Search?

cocoindex-io (a GitHub organization) maintains it in cocoindex-io/cocoindex-code, which has 2,743 GitHub stars. The repository was last updated on October 6, 2026.

Source: cocoindex-io/cocoindex-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.