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.
git clone --depth 1 https://github.com/gosha70/code-copilot-teamWrote 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/commands/gosha70/code-copilot-team/cooldown)<a href="https://agentmods.dev/commands/gosha70/code-copilot-team/cooldown"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/cooldown/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.
<a href="https://agentmods.dev/commands/gosha70/code-copilot-team/cooldown"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/cooldown.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00686 |
| Opus 5.5 | $0.00000 | $0.00274 |
| Sonnet 5.5 | $0.00000 | $0.00137 |
| Haiku 4.5 | $0.00000 | $0.00069 |
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 1mo 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 — 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.mdfiles and pick the highestNN. That's the most recent closed cycle; cooldown reports against it. Confirm with the user before proceeding. Ifspecs/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→ suggestshipped. - Some
done, some not → suggestshipped(partial) orshelved. Ask the user. - No scopes
done→ suggestshelved. Ask the user to confirm.
Use AskUserQuestion: "Was the bet <pitch-id> shipped or shelved?" — shipped | shelved.
4. Update pitch frontmatter
bet_status:frombuilding→shippedorshelvedper 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 logsince cycle end - List pitches shaped during cooldown
- Recommend candidates for the next betting table
- Write
specs/retros/cooldown-after-<NN>.md
7. Report
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.
- 1mo ago First seen · 58 lines · 0 tokens per session scan A e43f2f364771
cooldown is a command published in the GitHub repository gosha70/code-copilot-team (7 stars, last pushed 4d 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.
Other commands, from other repositories
portfolio
Show a read-only hub-wide portfolio of canonical Ideas and active Projects without duplicating topic-owned records.
story-continue
Resume an interrupted story from where you left off.
prp-prd
Interactive PRD generator - problem-first, hypothesis-driven product spec with back-and-forth questioning.
sdd
A command that creates three connected planning files for a software feature: requirements, design, and tasks.
project
Manage projects inside a topic wiki. Projects are folders under output/projects/ that group related outputs (playbooks, images, code, data) with a goal captured in WHY.md.
traceability-gen
A command that rebuilds a Markdown table linking requirements to project plans and tests. It reads requirement files, plan files, and test markers, then records what is planned or covered.