ccc-relay

ccc-relay is a skill for Claude Code, Codex from KevinZai/commander. It costs 45 tokens per session (3,240 once invoked), scanned A, original, MIT.

A workflow that chains separate agent sessions so the output of one becomes the input to the next. For example, a specification session can hand work to a build session, then to review and merge sessions.

In plain words
What is it for?
Use it to connect planning, implementation, review, and merge loops, with parallel work inside a stage when needed.
Why use it?
It separates long projects into independently managed stages while passing progress between them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: $skill-name invocation.

Good fit Use it to connect planning, implementation, review, and merge loops, with parallel…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kevinzai/commander/ccc-relay
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.

Any agent
npx skills add KevinZai/commander --skill ccc-relay
Clone the repo
git clone --depth 1 https://github.com/KevinZai/commander

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ccc-relay

README.md
[![agentmods](https://agentmods.dev/badge/skills/kevinzai/commander/ccc-relay.svg)](https://agentmods.dev/skills/kevinzai/commander/ccc-relay)
Your own site
<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>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,240 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00045 $0.03240
Opus 5 $0.00023 $0.01620
Sonnet 5 $0.00009 $0.00648
Haiku 4.5 $0.00005 $0.00324

Measured 3d ago against content hash 88a6dc0701b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

commander/cowork-plugin-codex/skills/ccc-relay/SKILL.md · 154 lines

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-relay composes 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:

  1. Link A runs as a normal gated loop (e.g. a /goal spec loop: "produce a plan file with acceptance criteria, stop after 5 tries").
  2. On convergence, Link A writes its result and a completion marker into .claude/loop-state/<relay-name>.json — it sets relay.phase to done and fills the handoff block.
  3. The next link is launched by whichever mechanism fits the surface:
    • Cloud / unattended/schedule fires the next loop (survives a closed laptop — the right default for a real relay).
    • Cowork Desktop → a spawn_task chip offers to spin the next link into its own session (one click).
    • CLI/spawn launches the next session as a peer (see ccc-spawn.md).
  4. Link B consumes the handoff block as its brief, runs its own gated loop, and repeats the pass — through review, then stops at merge for an explicit human GO.

Read the full file on GitHub · 154 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. 3d ago First seen · 154 lines · 45 tokens per session scan A 88a6dc0701b4

Subscribe to this mod's changes

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.

Related

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.

greenpolo/cc-multi-cli-plugin · 29 tokens

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…

andisab/swe-marketplace · 86 tokens

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.…

andisab/swe-marketplace · 85 tokens

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…

andisab/swe-marketplace · 158 tokens

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…

bcanfield/agentic-tech-debt · 76 tokens

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.

bcanfield/agentic-tech-debt · 74 tokens