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 skills add KevinZai/commander --skill ccc-relaygit clone --depth 1 https://github.com/KevinZai/commanderWrote 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/kevinzai/commander/ccc-relay)<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-relay"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-relay.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 | $0.00045 | $0.03240 |
| Opus 5 | $0.00023 | $0.01620 |
| Sonnet 5 | $0.00009 | $0.00648 |
| Haiku 4.5 | $0.00005 | $0.00324 |
Grade A, and why
ccc-relay 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-relay — Cross-Session Loop Chaining
$ccc-loop iterates inside one session. $ccc-relay chains separate sessions: an always-on spec loop hands its result to a build loop, which hands to a review loop, which hands to merge — each a distinct, independently-gated loop that launches the next automatically when its own stop condition is met. This is the "Finn Loop" pattern: not one agent looping, but a relay team of loops passing a baton.
$ccc-relaycomposes three primitives instead of re-implementing them — read those skills for the mechanics this one orchestrates:
ccc-loop— the loop taxonomy, the should-loop gate, the state-file convention, verifier-separation. Each link in a relay is one loop from that taxonomy.ccc-fleet— parallelism within a link (fan out the build across worktrees). A relay is sequential across links; a fleet is parallel within one.commands/ccc-spawn.md(/spawn) — the CLI mechanism for launching the next session as a peer when you're at a terminal.
What it is
A relay is a directed chain of loop sessions. Each link is a real loop (turn/goal/time/proactive — see ccc-loop), runs to its own stop condition, then triggers the next link and exits. No human re-prompts between links.
The canonical chain:
spec loop ──▶ build loop ──▶ review loop ──▶ merge (human GO)
$ccc-plan $ccc-build $ccc-review $ccc-ship
+ /goal + /goal + /goal (gated — never auto)
Baton pass, per link:
- Link A runs as a normal gated loop (e.g. a
/goalspec loop: "produce a plan file with acceptance criteria, stop after 5 tries"). - On convergence, Link A writes its result and a completion marker into
.claude/loop-state/<relay-name>.json— it setsrelay.phasetodoneand fills thehandoffblock. - The next link is launched by whichever mechanism fits the surface:
- Cloud / unattended →
/schedulefires the next loop (survives a closed laptop — the right default for a real relay). - Cowork Desktop → a
spawn_taskchip offers to spin the next link into its own session (one click). - CLI →
/spawnlaunches the next session as a peer (seeccc-spawn.md).
- Cloud / unattended →
- Link B consumes the
handoffblock as its brief, runs its own gated loop, and repeats the pass — throughreview, then stops atmergefor an explicit human GO.
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 · 154 lines · 45 tokens per session scan A 88a6dc0701b4
ccc-relay is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 3,240 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
multi-plan-handoff
Auto-detect plan files in conversation context and pass them to multi: execute subagents by reference, not by paraphrase.
skill-dev
Use this skill when creating or refining Claude Code skill definitions. Skills are model-invoked capabilities that Claude activates autonomously based on context. Helps design focused skills with discovery-optimized descriptions, proper directory structures, and supporting resources. Automatically invoked when user…
command-dev
Use this skill when creating or refining custom Claude Code slash commands. Slash commands are user-invoked reusable prompts that can accept arguments, reference files, and execute bash operations. Helps design command syntax, argument handling, file references, bash execution, and frontmatter configuration.…
mcp-tool-dev
Create MCP tools — individual tool functions exposed via Model Context Protocol. Use this skill whenever users mention MCP tools, tool handlers, tool functions, tool definitions, or want to add capabilities to an MCP server. Also use when the conversation involves designing tool schemas, writing tool descriptions, or…
debt-ops-init
Write or refresh a "Tech debt operations" section in the project's AGENTS.md so the team shares one source of truth for debt-ops disciplines. Run ONLY when the user explicitly asks to set up, install, or initialize debt-ops disciplines — never auto-invoke. Idempotent; only the managed section changes, other sections…
debt-ops-metrics
Print a debt-ops health summary from the metrics log, covering registration rate, feedback action rate, ADR creation, and AI-authored share. Use when the user asks for "debt-ops metrics", "debt health", "registry stats", or a tech-debt health summary. Read-only, never writes the log.