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.
curl -O https://raw.githubusercontent.com/codingriver/upilot/main/AGENTS.mdgit clone --depth 1 https://github.com/codingriver/upilotWrote 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/instructions/codingriver/upilot/agents-md)<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.
<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>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 | $0.01810 | $0.01810 |
| Opus 5.5 | $0.00724 | $0.00724 |
| Sonnet 5.5 | $0.00362 | $0.00362 |
| Haiku 4.5 | $0.00181 | $0.00181 |
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.
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
mainwithgh 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 inpackage.jsonorupilotserver~/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. SeeDocumentation~/UP001-UP009-Delivery.mdfor 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 downstreamBuild UPilot MCP Server EXErun 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 releasemanifest.jsonversions match the requested version. Confirm the build's local EXE/manifest/checksum and--versionverification 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.
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.
- 14d ago Changed · +12 lines · +603 tokens per session 34e34f9b9328
- 1mo ago Changed · +4 lines · +327 tokens per session 36a25adddfd4
- 1mo ago Changed · -13 tokens per session 42206a5b9371
- 1mo ago Changed · +2 lines · +164 tokens per session 3007a4d9384e
- 2mo ago First seen · 28 lines · 729 tokens per session scan A 332cfd128f30
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.
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.
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).
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.
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).
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.
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).