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/geval-labs/geval/copilot-instructionsgit clone --depth 1 https://github.com/geval-labs/gevalWrote 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/geval-labs/geval/copilot-instructions)<a href="https://agentmods.dev/instructions/geval-labs/geval/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/geval-labs/geval/copilot-instructions.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 | $0.00846 | $0.00846 |
| Opus 5 | $0.00423 | $0.00423 |
| Sonnet 5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
geval copilot-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 5d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Geval - AI Coding Instructions
Project Overview
Geval is a decision orchestration and reconciliation tool for AI systems. It consumes signals (JSON) and policy (YAML), evaluates all rules (unique priorities; 1 = highest), surfaces every match, applies the best-priority winner per policy, and merges policies/contracts with worst_case (BLOCK > REQUIRE_APPROVAL > PASS). It does not run evals, call APIs, or compute metrics—it only reconciles your rules against your signals.
Core Philosophy: Geval has no “brain.” You provide signals and rules; Geval applies the rules and returns one outcome. Same inputs + same policy = same outcome.
Repository Structure
- geval/ – Rust crate (the only product)
- src/ – CLI and engine (commands, evaluator, signals loader, policy parser)
- docs/ – User docs (installation, GitHub Actions, signals and rules, auditing)
- examples/ – Sample
signals.jsonandpolicy.yamlfor local/CI use - scripts/ – e.g.
generate_signals.pyfor CI demo
- .github/workflows/ – CI (build + test Rust) and release (build binary on tag push)
- Root: README, CONTRIBUTING, LICENSE, CODE_OF_CONDUCT
There are no npm packages, no TypeScript, no Turborepo. The artifact is a single Rust binary distributed via GitHub Releases.
Build and Test
- Build:
cargo build --release --manifest-path geval/Cargo.toml - Test:
cargo test --manifest-path geval/Cargo.toml - Binary:
geval/target/release/geval(orgeval.exeon Windows)
Run from repo root: ./geval/target/release/geval demo or geval check --signals ... --policy ... once the binary is on PATH.
CLI and Exit Codes
- Commands:
geval demo,geval init,geval check,geval explain,geval approve/geval reject(seegeval --help). - Exit codes (for CI):
0– PASS1– REQUIRE_APPROVAL2– BLOCK- Non-zero on error (e.g. missing file, invalid JSON/YAML).
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.
- 5d ago First seen · 57 lines · 846 tokens per session scan A 801bcb8065a5
geval copilot-instructions.md is an instructions file published in the GitHub repository geval-labs/geval (44 stars, last pushed 5mo ago), licensed MIT. It adds 846 tokens to every session, about $0.0042 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 2026-08-30.
Other instructions, from other repositories
oumi AGENTS.md
AGENTS.md instructions for oumi-ai/oumi, covering agent instructions, publication policy and working with contributions.
oumi CLAUDE.md
Claude Code instructions for oumi-ai/oumi: Instructions for coding agents live in AGENTS.md — read that file. It covers the publication policy (never push, fork, or open a pull request without the developer's explicit per-instance approval) and points at CONTRIBUTING.md for the contribution workflow.
argus-validation-benchmarks CLAUDE.md
Instructions for pensar-x/argus-validation-benchmarks, covering project overview, what you're building, the goal, success criteria and what is apex?.
evals4j CLAUDE.md
Instructions for dvarahq/evals4j, covering evals4j, layout, build, parity discipline and releasing.
tracelens CLAUDE.md
Instructions for ssf0409/tracelens, covering tracelens - development guide, project overview, ownership boundary, tracelens owns and downstream projects own.
evals-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/evals-mcp-server, covering developer protocol, this server, core rules, patterns and tool.