What is RepoPilot AGENTS.md?

A repository instruction file for RepoPilot, an automated system that responds to GitHub events, analyzes repository problems, creates patches, and sends pull requests for review. It describes its architecture and operating restrictions.

Use it when developing RepoPilot’s GitHub, agent orchestration, approval, evidence, database, monitoring, or pull-request workflows.

It keeps development aligned with the project’s required workflow and approval boundaries. In particular, it distinguishes actions an agent may automate from actions that need human approval, such as merging or changing secrets.

How wellkilo/RepoPilot configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to wellkilo/RepoPilot. 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/wellkilo/RepoPilot/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/wellkilo/RepoPilot

Made for: Codex, OpenCode.

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/wellkilo/repopilot/agents-md/github.svg)](https://agentmods.dev/instructions/wellkilo/repopilot/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/wellkilo/repopilot/agents-md"><img src="https://agentmods.dev/badge/instructions/wellkilo/repopilot/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/wellkilo/repopilot/agents-md"><img src="https://agentmods.dev/badge/instructions/wellkilo/repopilot/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 727 This file is loaded in full into every session.

When invoked 727 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	$0.00727	$0.00727
Opus 5.5	$0.00291	$0.00291
Sonnet 5.5	$0.00145	$0.00145
Haiku 4.5	$0.00073	$0.00073

Measured 2mo ago against content hash b38874c5e2a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

RepoPilot AGENTS.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 2mo 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.

AGENTS.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RepoPilot Development Contract

Mission

RepoPilot is an open-source, auditable repository-maintenance AgentTeam. It must maintain a real end-to-end loop:

GitHub event -> AgentTeams orchestration -> analysis -> patch -> pull request -> CI verification -> approval/audit -> runbook

Authoritative Constraints

AgentTeams v1.2.2 is the orchestration foundation. Do not replace it with a custom multi-agent simulator.
The default execution policy is pull_request_only.
RepoPilot may create branches, commits, comments, and pull requests automatically.
Merge, branch deletion, destructive rollback, permission changes, and secret changes require explicit human approval.
Runtime integrations use real GitHub, Matrix, MCP, PostgreSQL, and OpenTelemetry contracts. Tests may isolate pure functions, but production paths must not contain mock providers.
Secrets are supplied only through environment variables or the deployment secret manager and must never be committed.

Architecture

apps/control-plane: Fastify API, GitHub webhook ingestion, Matrix dispatch, evidence ledger, approval workflow, and Streamable HTTP MCP server.
apps/console: React evidence console for runs, Agent steps, approvals, traces, and runbooks.
packages/contracts: shared Zod schemas and TypeScript types.
deploy/agentteams: AgentTeams Worker and Team resources.
skills: reusable RepoPilot Agent Skills, plus installation metadata for official Alibaba Cloud Skills.
docs: API, method, architecture, security, roadmap, and operational documentation.
testbed: source template for the intentionally defective public/private demo repository.

Development Flow

Confirm the contract and relevant external API before implementation.
Update API.md and Method.md when an input, output, state transition, or external method changes.
Add focused unit tests for policies, schemas, evidence hashing, and state transitions.
Add integration tests for PostgreSQL, HTTP routes, GitHub webhook verification, and MCP calls.
Run pnpm lint, pnpm typecheck, pnpm test, and the relevant integration tests.
Preserve evidence for manual end-to-end validation under artifacts/; do not commit secrets or access tokens.

Read the full file on GitHub · 64 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.

2mo ago First seen · 64 lines · 727 tokens per session scan A b38874c5e2a4

Subscribe to this mod's changes

RepoPilot AGENTS.md is an instructions file published in the GitHub repository wellkilo/RepoPilot (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 727 tokens to every session, about $0.0029 per session on Opus 5.5. 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.

Building agents Multi-Agent agentteams github-automation mcp opentelemetry postgresql

RepoPilot AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
RepoPilot AGENTS.mdwellkilo/RepoPilot	Instructions file	3	2mo ago	Apache-2.0	A	727	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

RepoPilot: Instructions file for Codex