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.
npx agentmods add rules/gosha70/code-copilot-team/provider-collaboration-protocolgit clone --depth 1 https://github.com/gosha70/code-copilot-teamWhat 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 | $0.00024 | $0.00948 |
| Opus 5 | $0.00012 | $0.00474 |
| Sonnet 5 | $0.00005 | $0.00190 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
provider-collaboration-protocol 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Provider Collaboration Protocol
Rules governing cross-provider peer review in dual-copilot sessions.
Session Flags
Peer review is enabled per-session via launcher flags:
--peer-review [provider-name]— enable peer review; optional provider override.--peer-review-off— disable peer review.--peer-review-scope code|design|both— review scope (default:both).
Environment variables set by launcher:
CCT_PEER_REVIEW_ENABLED—trueorfalse.CCT_PEER_PROVIDER— explicit provider name or empty (use profile default).CCT_REVIEW_COMMITS— commit strategy:single,per-round, orsquash(default:squash).CCT_REVIEW_MAX_ROUNDS— max review rounds before breaker (default: 5).
Review Flow
Peer review is agent-driven via /review-submit, not triggered by stop hooks.
- Build agent completes work, commits, and runs
/review-submit. /review-submitinvokesreview-round-runner.shwhich spawns a reviewer LLM in a read-only sandbox.- Runner writes structured findings to
.cct/review/findings-round-N.jsonand returns a verdict. - On FAIL: agent addresses findings, commits fixes, and runs
/review-submitagain. - On PASS: runner writes
loop-summary.jsonand collaboration artifact. Agent proceeds to/phase-complete. - On BREAKER: runner writes
breaker-tripped.json. Agent stops. Human runs/review-decide.
The stop hook (peer-review-on-stop.sh) validates that loop-summary.json exists with PASS or approved bypass — it does not initiate review. Plan-phase sessions are exempt.
See review-loop.md for the full loop protocol, finding schema, and circuit breaker details.
Artifact Schema
Collaboration artifacts live under specs/<feature-id>/collaboration/.
Artifact types:
plan-consult.md— peer review of the plan phase.build-review.md— peer review of the build phase.
Frontmatter (aligned with SDD conventions)
---
feature_id: [feature-id]
date: [YYYY-MM-DD]
status: [draft | final]
phase: [plan | build]
mode: [consult | review]
subject_provider: [provider that did the work]
peer_provider: [provider that reviewed]
peer_profile: [profile name from providers.toml]
runner_fingerprint: [command template hash + provider version]
verdict: [PASS | FAIL | INCONCLUSIVE]
blocking_findings_open: [integer]
target_ref: [git ref]
---
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.
- 2d ago First seen · 102 lines · 24 tokens per session scan A d21306c74d72
provider-collaboration-protocol is a cursor rule published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 948 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 2026-08-31.
Other cursor rules, from other repositories
cuopt-skill-evolution
Trigger skill evolution — after solving non-trivial problems, propose skill updates.
cursorrules
See CLAUDE.md for full context. Quick rules.
moyu
当检测到过度工程模式时自动激活：修改用户未要求的代码、创建不必要的抽象层、 添加未要求的注释/文档/测试、引入不必要的依赖、重写整个文件而非最小编辑、 diff 超出请求范围。用户说"太多了"、"只改 X"、"简单点"时触发。 Activates on over-engineering: modifying unrequested code, unnecessary abstractions, unsolicited comments/docs/tests, unrequested dependencies, full file rewrites, scope-exceeding diffs. Triggers on "too…
cursorrules
This repository contains a structured skill library for AI-assisted product development. Skills are in skills//SKILL.md. Read the relevant SKILL.md before generating any artifact.
cursorrules
AgentAnycast is a decentralized P2P runtime for the A2A (Agent-to-Agent) protocol.
homunculus
Homunculus self-evolving AI assistant. Use when user asks about evolution cycles, goal trees, system status, instincts, or skills. Provides routing to detailed evolution workflows.