hermes-skilleval: Instructions file for Codex

AGENTS.md

hermes-skilleval AGENTS.md is an instructions file for Codex, OpenCode from Raidriar7170/hermes-skilleval. It costs 363 tokens per session, scanned A, original, MIT.

A contributor guide for Hermes SkillEval, a system that evaluates how AI agents route tasks to skills and verifies their results. It defines evidence types, evaluation boundaries, release rules, and protected files.

In plain words
What is it for?
Use it when changing the skill router, evaluators, verification rules, benchmark protocols, release logic, or phase documentation.
Why use it?
It prevents agents from confusing offline replay with live-agent evidence or replacing deterministic checks with subjective review. It also protects benchmark labels, historical records, and release behavior from accidental changes.

Instructions file for CodexOpenCode

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

This is Raidriar7170/hermes-skilleval's own configuration. It tells Codex and OpenCode how to work on hermes-skilleval 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 hermes-skilleval configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Raidriar7170/hermes-skilleval. 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/Raidriar7170/hermes-skilleval/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Raidriar7170/hermes-skilleval

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 hermes-skilleval AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/raidriar7170/hermes-skilleval/agents-md.svg)](https://agentmods.dev/instructions/raidriar7170/hermes-skilleval/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/raidriar7170/hermes-skilleval/agents-md"><img src="https://agentmods.dev/badge/instructions/raidriar7170/hermes-skilleval/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 363 This file is loaded in full into every session.
When invoked 363 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 $0.00363 $0.00363
Opus 5 $0.00181 $0.00181
Sonnet 5 $0.00073 $0.00073
Haiku 4.5 $0.00036 $0.00036

Measured 8d ago against content hash 4b5224d162a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

hermes-skilleval 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 8d 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 · 28 lines

What it actually says

Hermes SkillEval Contributor Instructions

  • Read CONTEXT.md, README.md, the relevant docs/v0.3/ protocol, and the nearest existing implementation or docs before editing.
  • Keep one PR scope at a time. Do not bundle unrelated refactors or release work into protocol, benchmark, runtime, or documentation changes.
  • Preserve existing CLI behavior, release gates, tests, and historical Phase 10-18 artifacts unless a later approved change explicitly updates them.
  • Do not modify src/hermes_skilleval/**, tests/**, historical phase docs, or release logic for v0.3 PR-0.
  • Treat the SkillRouter scored set as evaluation-only: no training, tuning, threshold selection, variant selection, or hard-negative mining on final scored labels.
  • Preserve Phase 10 as deterministic offline replay evidence. Do not describe it as live-agent evidence.
  • Use deterministic verifiers as the primary live-agent success judge. LLM or human review may diagnose failures but must not replace verifier outcomes.
  • Keep VALID_EVIDENCE, INVALID_EVIDENCE, and REVIEW_REQUIRED separate from router promotion decisions such as KEEP_BASELINE and PROMOTE_CANDIDATE.
  • Never commit external full datasets, model checkpoints, embedding caches, credentials, raw auth files, private host details, or unsanitized agent traces.
  • Mark unavailable evidence as UNAVAILABLE; do not fabricate source, temporal, cost, token, activation, or verifier fields.
  • Do not claim a benchmark result, live-agent result, release decision, or public-readiness posture that was not produced by a committed command and recorded artifact.
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. 8d ago First seen · 28 lines · 363 tokens per session scan A 4b5224d162a8

Subscribe to this mod's changes

hermes-skilleval AGENTS.md is an instructions file published in the GitHub repository Raidriar7170/hermes-skilleval (124 stars, last pushed 1mo ago), licensed MIT. It adds 363 tokens to every session, about $0.0018 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.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 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 · 6,785 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 · 7,296 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 · 4,469 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens