stage-coach

stage-coach is a skill for Claude Code, Codex from Snowflake-Labs/cocoplus. It costs 19 tokens per session (543 once invoked), scanned A, original, MIT.

A review process that sends completed CocoFlow stages to a separate coach model for quality scoring.

In plain words
What is it for?
Use it to process queued review requests, inspect declared inputs and outputs, record scores, and track missing downstream artifacts.
Why use it?
It keeps the model producing an artifact separate from the model reviewing it, which provides an independent check on stage output.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to process queued review requests, inspect declared inputs and outputs, record scores, and track missing downstream artifacts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/snowflake-labs/cocoplus/stage-coach
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 Snowflake-Labs/cocoplus --skill stage-coach
Clone the repo
git clone --depth 1 https://github.com/Snowflake-Labs/cocoplus

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 stage-coach

README.md
[![agentmods](https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/stage-coach/github.svg)](https://agentmods.dev/skills/snowflake-labs/cocoplus/stage-coach)
Your own site
<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/stage-coach"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/stage-coach/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.

agentmods 80×15 button for stage-coach

Your own site · 80×15
<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/stage-coach"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/stage-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 543 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 $0.00019 $0.00543
Opus 5 $0.00010 $0.00271
Sonnet 5 $0.00004 $0.00109
Haiku 4.5 $0.00002 $0.00054

Measured 5d ago against content hash a1ef08307282, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

stage-coach 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 5d 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.

.cortex/skills/cocosentinel/stage-coach.skill.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use this skill for queued per-stage coach reviews from .cocoplus/sentinel/coach-requests.jsonl.

Objective

Evaluate completed CocoFlow stages with a separate coach model so generator and critic remain structurally separated.

Workflow

  1. Verify .cocoplus/ exists.
  2. Read .cocoplus/sentinel/coach-requests.jsonl.
  3. For each queued request, collect:
    • stage role and task brief from .cocoplus/flow.json
    • declared artifacts.reads and artifacts.writes
    • produced artifact paths under .cocoplus/flow/artifacts/<run-id>/
    • downstream missing artifact status
  4. Verify coach_model differs from the executor model. If not, write .cocoplus/sentinel/known-gaps.jsonl and skip the request.
  5. Run an external coach evaluation using the configured coach model.
  6. Write .cocoplus/sentinel/stage-quality.jsonl:
{
  "ts": "...",
  "stage_id": "function-designer",
  "score": 7,
  "reasoning": "Specific evidence-backed rationale.",
  "attributed_to": "function-designer",
  "coach_model": "haiku"
}
  1. Mark consumed requests as processed by writing .cocoplus/sentinel/coach-requests.processed.jsonl.

Scoring

  • 8-10: usable output with clear artifact handoff
  • 5-7: core output exists but a declared contract, evidence item, or handoff is incomplete
  • <5: missing required output, ungrounded result, or downstream blocker attributable to this stage

Exit Criteria

  • Each score cites produced or missing artifacts.
  • The coach never evaluates its own generation.
  • Missing artifacts are attributed to the stage that declared them.
  • Console-readable stage-quality.jsonl is updated.

Anti-Rationalization

Shortcut / Temptation Why It Fails
Treat the skill as complete because the file exists Skill contracts must describe observable behavior and verification, not just command names.
Skip artifact and safety checks for a small command Small commands still mutate state or guide execution; preserve the same gates.

Read the full file on GitHub · 63 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. 5d ago First seen · 63 lines · 19 tokens per session scan A a1ef08307282

Subscribe to this mod's changes

stage-coach is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 6d ago), licensed MIT. It adds 19 tokens to every session and 543 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 2026-09-03.