It helps run read-only code or design reviews, record findings, choose a commit strategy, and repeat reviews until the work passes.

It gives multi-agent projects a defined way to submit findings, fix failures, and stop after a limited number of review rounds.

How gosha70/code-copilot-team configures GitHub Copilot

Q: What is code-copilot-team provider-collaboration-protocol.instructions.md?

A process for having one coding agent review another agent’s work through structured review rounds.

Reuse

Borrowing it

Nothing to install: this file belongs to gosha70/code-copilot-team. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/gosha70/code-copilot-team/master/adapters/github-copilot/.github/instructions/provider-collaboration-protocol.instructions.md

Clone the repo

git clone --depth 1 https://github.com/gosha70/code-copilot-team

Made for: GitHub Copilot.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gosha70/code-copilot-team/provider-collaboration-protocol.svg)](https://agentmods.dev/instructions/gosha70/code-copilot-team/provider-collaboration-protocol)

Your own site

<a href="https://agentmods.dev/instructions/gosha70/code-copilot-team/provider-collaboration-protocol"><img src="https://agentmods.dev/badge/instructions/gosha70/code-copilot-team/provider-collaboration-protocol.svg" alt="Measured on agentmods" height="20"></a>

Per session 921 This file is loaded in full into every session.

When invoked 921 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00921	$0.00921
Opus 5	$0.00461	$0.00461
Sonnet 5	$0.00184	$0.00184
Haiku 4.5	$0.00092	$0.00092

Measured 3d ago against content hash d8ad55bc1557, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

code-copilot-team provider-collaboration-protocol.instructions.md 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 3d 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/github-copilot/.github/instructions/provider-collaboration-protocol.instructions.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 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 — true or false.
CCT_PEER_PROVIDER — explicit provider name or empty (use profile default).
CCT_REVIEW_COMMITS — commit strategy: single, per-round, or squash (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-submit invokes review-round-runner.sh which spawns a reviewer LLM in a read-only sandbox.
Runner writes structured findings to .cct/review/findings-round-N.json and returns a verdict.
On FAIL: agent addresses findings, commits fixes, and runs /review-submit again.
On PASS: runner writes loop-summary.json and 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]
---

Read the full file on GitHub · 101 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.

3d ago First seen · 101 lines · 921 tokens per session scan A d8ad55bc1557

Subscribe to this mod's changes

code-copilot-team provider-collaboration-protocol.instructions.md is an instructions file published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed today), licensed MIT. It adds 921 tokens to every session, about $0.0046 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 2026-09-03.

Building agents Code review

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

code-copilot-team: Instructions file for GitHub Copilot