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 instructions/lcv-ideas-software/cross-review/agents-mdgit clone --depth 1 https://github.com/LCV-Ideas-Software/cross-reviewWrote 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/lcv-ideas-software/cross-review/agents-md)<a href="https://agentmods.dev/instructions/lcv-ideas-software/cross-review/agents-md"><img src="https://agentmods.dev/badge/instructions/lcv-ideas-software/cross-review/agents-md.svg" alt="Measured on agentmods" 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 | $0.02107 | $0.02107 |
| Opus 5 | $0.01053 | $0.01053 |
| Sonnet 5 | $0.00421 | $0.00421 |
| Haiku 4.5 | $0.00211 | $0.00211 |
Grade A, and why
cross-review 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 today.
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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - cross-review
Pointer for AI agents working in this repository.
Project
- Repository:
https://github.com/LCV-Ideas-Software/cross-review - Package:
@lcv-ideas-software/cross-review - Site:
https://cross-review.lcv.dev - Branch:
main - License: Apache-2.0
Runtime Shape
This repository is the source of the cross-review MCP server: API-first
multi-model cross-review with unanimous convergence gates. Binaries published
by the package: cross-review and cross-review-dashboard.
Mandatory Gates
npm test
npm run check
npm run lint
npm run biome
npm run typecheck
npm run format:check
npm pack --dry-run
Regression suites are versioned (npm run lists the full set); a change that
touches a guarded contract must run the matching regression before closure.
Release
Publishing runs on GitHub's documented model with no manual gesture: a push to
main that changes the package.json version publishes the package to
npmjs.com through npm Trusted Publishing (OIDC) with provenance, mirrors it to
GitHub Packages, and then records the Release with the run's own token. The
repository owns no tagging or dispatch automation and holds no publishing
secret.
The merge is the deliberate act. A pull request that bumps the version
publishes when it lands, so a version that must not be published must not be
merged. The manifest version has to be a plain three-part numeric version,
never a prerelease: the workflow refuses anything else before deriving the
vXX.XX.XX tag. The push that bumps the version is the push that
publishes: the manifest version is compared with the one the previous head
declared, so a push that changes package.json without changing the version,
such as a Dependabot merge, ends as a no-op that says so. A run that dies
after a registry write is resumed with GitHub's own recovery,
gh run rerun --failed <run-id>, which reruns only the failed jobs and keeps
the outputs of the ones that passed, so nothing is published twice; the
workflow refuses to start over a version npm already serves and says so.
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.
- today Changed · +26 lines · +340 tokens per session 40bc34c760ea
- 5d ago First seen · 143 lines · 1,767 tokens per session scan A ca34b1af7176
cross-review AGENTS.md is an instructions file published in the GitHub repository LCV-Ideas-Software/cross-review (0 stars, last pushed today), licensed Apache-2.0. It adds 2,107 tokens to every session, about $0.0105 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 instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.