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/team-review)<a href="https://agentmods.dev/commands/gosha70/code-copilot-team/team-review"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/team-review/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/team-review"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/team-review.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 | $0.00287 |
| Opus 5.5 | $0.00000 | $0.00115 |
| Sonnet 5.5 | $0.00000 | $0.00057 |
| Haiku 4.5 | $0.00000 | $0.00029 |
Grade A, and why
team-review 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.
What it actually says
/team-review
Coordinate a multi-role review of the current change.
When to Run
- After any change to
content/, either wrapper, the publishing scripts, or CI. - Before tagging a release.
Procedure
- Team Lead opens by stating the change in one sentence and which domains it touches: content, jvm-wrapper, python-wrapper, scripts, .github.
- Spawn the relevant specialist via the Agent tool. Use the delegation prompt in
PROJECT.mdand substitute the role. - Each role checks its constraints:
- Content Curator — manifest version bumped if entries were removed; sources cited; LICENSE-DATA still accurate.
- JVM Wrapper Engineer — loader API unchanged unless explicitly versioned; tests pass; build reads version from manifest, never hardcoded.
- Python Wrapper Engineer — loader API mirrors JVM; tests pass; mypy strict clean; package_data still resolves via
importlib.resources. - Release & CI Engineer — schema validators still gate the PR; publish workflow's preflight version check still wired; secrets unchanged.
- Team Lead synthesizes findings, blocks merge on any failure, and (only after green) approves the change.
Output
A short review summary in the PR description listing each role, the checks they ran, and the disposition (PASS / FAIL / N/A).
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 · 22 lines · 0 tokens per session scan A 9f8715f674aa
team-review is a command published in the GitHub repository gosha70/code-copilot-team (7 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 287 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 2026-09-03.
Other commands, from other repositories
backlog
The project layer: milestones, epics, and user stories with refusing controllers — spec-seeded, sprint-ready.
sprint
Scope-boxed sprints over the backlog: one active sprint, explicit carry-over, a close that refuses to hide unfinished work.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
task-hunter.skeleton
The user's input is resolved according to the following rules.
task-conductor.skeleton
/task-conductor top 5 -> /task-conductor plan top 5 /task-conductor all -> /task-conductor plan all /task-conductor 3,5,8 -> /task-conductor plan 3,5,8.
task-master.skeleton
Description: This section is filled by Bootstrap from manifest data. Required manifest fields: project.description, stack.primary Example output.