Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add iliaal/ccc-plugin/plugin install ccc-toolsWrote 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/iliaal/ccc-plugin/ccc-onboard)<a href="https://agentmods.dev/commands/iliaal/ccc-plugin/ccc-onboard"><img src="https://agentmods.dev/badge/commands/iliaal/ccc-plugin/ccc-onboard/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/iliaal/ccc-plugin/ccc-onboard"><img src="https://agentmods.dev/badge/commands/iliaal/ccc-plugin/ccc-onboard.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.00815 |
| Opus 5.5 | $0.00010 | $0.00326 |
| Sonnet 5.5 | $0.00005 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
ccc-onboard 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard a project to cocoindex-code
Wraps ${CLAUDE_PLUGIN_ROOT}/bin/ccc-onboard and reports results to the user.
Step 1: Validate arguments
Arguments are in $ARGUMENTS. The first positional arg should be a path that exists. If it doesn't look like a directory path, stop and ask the user what to do.
Step 2: Run the onboarding script
Invoke the shell script via Bash:
${CLAUDE_PLUGIN_ROOT}/bin/ccc-onboard $ARGUMENTS
The script runs six steps: ccc init, apply standard excludes, ccc index, register MCP server, install git hooks (if repo), write local .claude/CLAUDE.md hint (if missing). Each step is idempotent or skippable, so a re-run on an existing project is safe.
Indexing on CPU can take 5-50 minutes depending on repo size. On CUDA it's roughly 6-10× faster. If the script looks like it will take more than ~2 minutes, run it with run_in_background: true and poll the output file.
Step 3: Parse and report
Report what the script actually did, not what it planned to do:
- Number of chunks indexed and the language breakdown from the
ccc indexoutput - Which MCP server name was registered (default or custom)
- Whether git hooks were installed, and in how many git directories under the project
- Whether the
.claude/CLAUDE.mdhint was written or already existed - Any warnings from the script (e.g., "claude mcp add failed", existing hooks skipped)
Step 4: Verify MCP connectivity
After the script completes, run:
claude mcp list
Confirm the new server appears as ✓ Connected. If it's ✗ Failed to connect, dig into why — the most common cause is that ccc mcp refuses to run outside an initialized project directory, which the wrapper sh -c "cd PATH && exec ccc mcp" handles but can fail if the path has spaces or special characters. Report the exact failure to the user.
Step 5: Quick sanity query
If everything looks connected, run one test search to prove the index is usable:
cd <project-path> && ccc search --limit 3 "<pick a term likely to match>"
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.
- 1mo ago First seen · 76 lines · 25 tokens per session scan A 7a6090a34a32
ccc-onboard is a command published in the GitHub repository iliaal/ccc-plugin (1 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 815 once invoked, about $0.0001 per session on Opus 5.5. 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
ia-verify
Run pre-PR verification chain: build, types, lint, tests, security scan, diff review.
announce
Draft X/Twitter announcement post (or thread) for the latest plugin release.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
sm-swab
Run slop-mop's iterative development loop for this repository.
release
Generate changelog, bump version, and create git tag.
review
Heavy multi-agent editorial review (4 specialist auditors in parallel).