cooldown

A command that closes a Shape Up cycle and prepares a cooldown report, a review of what happened during the cycle.

In plain words
What is it for?
Use it to close a cycle as shipped or shelved when appropriate, or to report on the most recently completed cycle.
Why use it?
It checks the active pitch and completed scopes before finalizing the cycle's outcome.

Command for Claude Code

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.

agentmods
npx agentmods add commands/gosha70/code-copilot-team/cooldown
Clone the repo
git clone --depth 1 https://github.com/gosha70/code-copilot-team

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 686 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00686
Opus 5 $0.00000 $0.00343
Sonnet 5 $0.00000 $0.00137
Haiku 4.5 $0.00000 $0.00069

Measured 2d ago against content hash e43f2f364771, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cooldown 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 2d 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.

adapters/claude-code/.claude/commands/cooldown.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Close out a cycle — invoke cooldown-report and finalize the active pitch's bet status.

Usage: /cooldown

Steps

1. Find the active pitch

Scan specs/pitches/*/pitch.md for bet_status: building.

  • 0 matches → no cycle to close. Continue to step 2 with active_pitch_id="".
  • 1 match → refuse. Resolve first.

  • exactly 1 → that's the active pitch.

2. Determine the cycle number

  • If an active pitch was found in step 1: read its cycle: frontmatter (e.g. 01). This is the cycle being closed.
  • If no active pitch: list specs/retros/cycle-NN.md files and pick the highest NN. That's the most recent closed cycle; cooldown reports against it. Confirm with the user before proceeding. If specs/retros/ is empty or does not exist, refuse — there is no cycle to report on.

3. Decide the bet outcome

If no active pitch was found in step 1, skip steps 3–5 and jump to step 6 (cooldown-report only — no frontmatter to mutate).

Otherwise read hill.json for the active pitch:

  • All scopes done → suggest shipped.
  • Some done, some not → suggest shipped (partial) or shelved. Ask the user.
  • No scopes done → suggest shelved. Ask the user to confirm.

Use AskUserQuestion: "Was the bet <pitch-id> shipped or shelved?" — shipped | shelved.

4. Update pitch frontmatter

  • bet_status: from buildingshipped or shelved per user's choice.

Append to bet log: | <YYYY-MM-DD> | <shipped|shelved> | Cycle NN closed. <one-line summary of hill final state>. |

5. Re-validate

Run bash ~/.claude/templates/sdd/validate-pitch.sh --pitch-id <pitch-id>. Refuse if it fails — restore previous state.

6. Invoke cooldown-report

Use the Agent tool with subagent_type: cooldown-report. Pass the cycle number that just finished.

The agent will:

  • Summarize bug fixes from git log since cycle end
  • List pitches shaped during cooldown
  • Recommend candidates for the next betting table
  • Write specs/retros/cooldown-after-<NN>.md

7. Report

Read the full file on GitHub · 58 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. 2d ago First seen · 58 lines · 0 tokens per session scan A e43f2f364771

Subscribe to this mod's changes

cooldown is a command published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 686 tokens. 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.