upilot: Instructions file for Codex

AGENTS.md

upilot AGENTS.md is an instructions file for Codex, OpenCode from codingriver/upilot. It costs 1,810 tokens per session, scanned A, original, MIT.

Repository instructions for UPilot, including its release process, testing checks, and planned improvements.

In plain words
What is it for?
Preparing UPilot releases, checking that changes are committed and pushed, starting the release workflow, and monitoring its build jobs.
Why use it?
They define how releases are authorized, versioned, triggered, and verified so repository changes follow the project’s rules.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is codingriver/upilot's own configuration. It tells Codex and OpenCode how to work on upilot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything upilot configures →

Reuse

Borrowing it

Nothing to install: this file belongs to codingriver/upilot. 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/codingriver/upilot/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/codingriver/upilot

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.

agentmods badge for upilot AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/codingriver/upilot/agents-md/github.svg)](https://agentmods.dev/instructions/codingriver/upilot/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/codingriver/upilot/agents-md"><img src="https://agentmods.dev/badge/instructions/codingriver/upilot/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.

agentmods 80×15 button for upilot AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/codingriver/upilot/agents-md"><img src="https://agentmods.dev/badge/instructions/codingriver/upilot/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,810 This file is loaded in full into every session.
When invoked 1,810 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01810 $0.01810
Opus 5.5 $0.00724 $0.00724
Sonnet 5.5 $0.00362 $0.00362
Haiku 4.5 $0.00181 $0.00181

Measured 14d ago against content hash 34e34f9b9328, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

upilot 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 14d 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 · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UPilot Repository Instructions

Release Workflow

  • Before handling this repository's release, release-status monitoring, or release-failure diagnosis, read the relevant sections of Documentation~/Release.md. The runbook supplies procedures, not permission to publish, retry, change files, or delete tags; a diagnosis-only request remains read-only.
  • Treat commands such as 发布版本 v0.3.22,并检查打包结果和版本号是否正确, 发布 v0.3.22, 触发发布版本 0.3.22, and semantically equivalent requests as explicit authorization to run the GitHub Actions workflow named 发布版本 from .github/workflows/prepare-release.yml.
  • Use the requested semantic version after normalizing it to vMAJOR.MINOR.PATCH. If the user requests the next version without specifying a number, inspect existing tags and use the next patch version unless the user states otherwise.
  • Trigger the workflow from main with gh workflow run prepare-release.yml --ref main -f version=<version>. Do not manually create or push the release tag, and do not manually maintain release versions in package.json or upilotserver~/pyproject.toml; the workflow owns those operations.
  • Unity release evidence is optional. When -f acceptanceRunId=<runId> is supplied, verify its provenance, age and source identity; a missing evidence run must not block release dispatch. Do not substitute a local summary for explicitly supplied evidence. See Documentation~/UP001-UP009-Delivery.md for the optional evidence workflow and source C→R contract.
  • Before triggering a release, verify that the intended release changes are committed and pushed to main. Do not include unrelated local changes without explicit authorization.
  • Preserve the repository's established check policy: do not enable optional checks, disable required checks, or change strictness just to retry or diagnose a release without an explicit requirement. Never report a skipped, disabled, or unknown check as passed.
  • After triggering, monitor both the 发布版本 run and its downstream Build UPilot MCP Server EXE run until completion. A successful dispatch alone is not a successful release.
  • Before reporting release success, verify both workflow conclusions, the tag-to-build commit identity, the GitHub release and expected assets, and that the tag's package.json, upilotserver~/pyproject.toml, and release manifest.json versions match the requested version. Confirm the build's local EXE/manifest/checksum and --version verification passed before publication; observe the remote asset list, but do not claim to have verified downloaded EXE bytes unless that was separately done. Report run URLs, commits/tag, asset and local hash results, and any unverified item clearly. Packaging/release success is not Unity compilation, EditMode, or business acceptance: report only coverage backed by actual evidence.
  • If either workflow fails or any version is inconsistent, do not report release success. Preserve the failure logs and identify the failed step and corrective action.
  • Do not automatically delete, move, or recreate a remote tag or overwrite a Release after failure. Recovery requires appropriate user authorization; when a new release is authorized, prefer a new patch version over reusing a failed tag. If dispatch or publication is uncertain, inspect the original run, tag, and Release before considering another request; do not automatically redispatch.

Read the full file on GitHub · 46 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.

  1. 14d ago Changed · +12 lines · +603 tokens per session 34e34f9b9328
  2. 1mo ago Changed · +4 lines · +327 tokens per session 36a25adddfd4
  3. 1mo ago Changed · -13 tokens per session 42206a5b9371
  4. 1mo ago Changed · +2 lines · +164 tokens per session 3007a4d9384e
  5. 2mo ago First seen · 28 lines · 729 tokens per session scan A 332cfd128f30

Subscribe to this mod's changes

upilot AGENTS.md is an instructions file published in the GitHub repository codingriver/upilot (0 stars, last pushed 13d ago), licensed MIT. It adds 1,810 tokens to every session, about $0.0072 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.

Related

Other instructions, from other repositories

skill-doctor github-automation.instructions.md

Instructions for evilstar2016/skill-doctor, covering github-automation, description, when to use and instructions.

evilstar2016/skill-doctor · 72 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 · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens