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/iliaal/ccc-pluginWrote 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-reindex)<a href="https://agentmods.dev/commands/iliaal/ccc-plugin/ccc-reindex"><img src="https://agentmods.dev/badge/commands/iliaal/ccc-plugin/ccc-reindex.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 | $0.00027 | $0.00487 |
| Opus 5 | $0.00014 | $0.00244 |
| Sonnet 5 | $0.00005 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
ccc-reindex 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 6d 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.
What it actually says
Force incremental ccc re-index
Wraps ccc index for cases when you want an immediate refresh without waiting for a commit/merge/checkout hook to fire.
Step 1: Resolve the target project
$ARGUMENTS is the project path. If empty, fall back to the current working directory. Verify the target has a .cocoindex_code/settings.yml — if not, stop and tell the user they need to run /ccc-onboard first.
Step 2: Pre-flight check
Run ccc daemon status to confirm the daemon is alive and to capture the pre-reindex state of the project (look for [idle] vs [indexing]). Save the current chunk count by running cd <project> && ccc status so you can report the delta after.
Step 3: Run the incremental index
cd <project> && ccc index
This is incremental — only changed files get re-processed. On an empty delta with a warm CUDA daemon it's 3-5 seconds. On a large delta (e.g., after a big merge), it's minutes.
If the command runs for more than ~30 seconds, background it via run_in_background: true and poll the output file until completion.
Step 4: Report the result
Parse the ccc index output and report:
- Files listed / added / deleted / reprocessed / unchanged
- Total chunks after (and delta vs. pre-count if you captured it)
- Any errors reported by the indexer
End with a one-line confirmation: <project>: <N> chunks, <M> files indexed, took <time>s.
Notes
- This is a no-op wrapper for
ccc index. The only reason to use it over callingccc indexdirectly via Bash is the structured pre/post reporting and daemon state check. - Do not run
ccc reset— that's what/ccc-resetis for. This command only forces an incremental refresh. - If the daemon isn't running,
ccc indexwill auto-start it; report the cold-start latency to the user.
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.
- 6d ago First seen · 44 lines · 27 tokens per session scan A 35ebc65e7698
ccc-reindex is a command published in the GitHub repository iliaal/ccc-plugin (1 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 487 once invoked, about $0.0001 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 commands, from other repositories
composite-actions
Generate, review, secure, and test composite GitHub Actions following best practices — full repo scaffold, interview-driven generation, PR creation on existing repos, SHA pinning, secrets-as-inputs, job summaries, and actionlint validation.
github-actions
Design, review, secure, and debug GitHub Actions workflows — reusable workflows, OIDC federation, SHA pinning, token scoping, promotion orchestration, and CI failure diagnosis.
datadog
Set up and troubleshoot Datadog — Agent deployment on Kubernetes, APM instrumentation, Log Management, Monitors, Dashboards, SLOs, Synthetic tests, and live incident investigation using the Datadog MCP server. Covers Terraform-managed Datadog resources.
fluxcd
FluxCD entry point — routes to the right workflow based on what you need. Live cluster issue → structured 5-workflow debug trace. Repo health check → 6-phase audit (discovery, validation, API compliance, best practices, security). Helm chart review → helmchart. Starts by asking one question to confirm the right mode.
linkerd
Linkerd-specific diagnostics — mTLS verification, proxy injection issues, authorization policy debugging, traffic management, and multi-cluster connectivity problems.
announce
Draft X/Twitter announcement post (or thread) for the latest plugin release.