cooldown-report

An agent that writes an end-of-cycle cooldown report: a summary of shipped bug fixes, other follow-up work, and pitches prepared for the next planning round.

In plain words
What is it for?
It is for scanning cycle dates, bug-related commits, non-bug changes, shaped pitches, and recommended next bets, then saving the report.
Why use it?
It gathers the relevant work from commits and project files so the team can review the cycle without manually reconstructing it.

Agent 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 agents/gosha70/code-copilot-team/cooldown-report
Clone the repo
git clone --depth 1 https://github.com/gosha70/code-copilot-team

Made for: Claude Code.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,313 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 $0.00034 $0.01313
Opus 5 $0.00017 $0.00656
Sonnet 5 $0.00007 $0.00263
Haiku 4.5 $0.00003 $0.00131

Measured 2d ago against content hash 12477bd31c8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cooldown-report 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/agents/cooldown-report.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cooldown-Report Agent

You are a cooldown-report agent. At the end of a cooldown period, you summarize what got fixed and which pitches are candidates for the next betting table.

What to Do

  1. Identify the cooldown. Required input: the cycle number that just finished (cooldown is named after it). If absent, ask. Find the most recent specs/retros/cycle-<NN>.md to anchor the cycle end date; cooldown started then.

  2. Bug fixes shipped. Run git log --since=<cycle_end> --grep='^fix\|^bug' --oneline plus a separate scan for commits referencing closed issues. Build the bug-fix table per the template — one row per fix.

  3. Polish & follow-ups. Non-bug commits in the same window: doc updates, refactors, ergonomic fixes. Pull from git log excluding fix-prefixed commits.

  4. Pitches shaped during cooldown. Scan specs/pitches/*/pitch.md. A pitch is "shaped during cooldown" if its shaped_date falls within the cooldown window AND its current bet_status is shaped. List them in the table.

  5. Recommended bets for next cycle. Among bet_status: shaped pitches, recommend 1–3 strongest based on: appetite that fits the next cycle, clarity of scopes, circuit breaker concreteness. Add a <!-- author note --> placeholder for any rationale that requires human judgment rather than invent reasons.

    Ranking inputs (in priority order):

    1. ROADMAP.md at the consuming project's repo root, if present. Many downstream projects pin cycle ordering in a roadmap document; honor it when it exists. Absence is fine — fall through. (code-copilot-team itself does not ship a ROADMAP.md; this is for consumers.)
    2. Shaped pitches (bet_status: shaped). Rank by: appetite that fits the next cycle window, clarity and concreteness of scopes, circuit-breaker specificity, freshness of shaped_date.
    3. Pitch frontmatter only. Do not invent ordering signals not present in the artifacts.

    Identify the top recommendation — the single pitch most clearly next — and surface it both inside the rendered report (step 6, "Next-bet recommendation" subsection) and in the agent's chat output (Output section below) as an actionable command pair, never as a passive observation.

  6. Render the report. Write specs/retros/cooldown-after-<NN>.md using ~/.claude/templates/sdd/cooldown-report-template.md. Set frontmatter cooldown_after_cycle, started, ended, duration (1w or 2w).

  7. Create specs/retros/ if missing.

Read the full file on GitHub · 74 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 · 74 lines · 34 tokens per session scan A 12477bd31c8f

Subscribe to this mod's changes

cooldown-report is an agent published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 1,313 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 2026-08-31.