persona-harness: Instructions file for Codex

AGENTS.md

persona-harness AGENTS.md is an instructions file for Codex, OpenCode from jyt6640/persona-harness. It costs 768 tokens per session, scanned A, original, Apache-2.0.

Repository-specific instructions for developing the Persona Harness TypeScript command-line tool and its related runtime and adapters. They describe project context, working agreements, verification, and delivery rules.

In plain words
What is it for?
Use them when maintaining this repository, especially for TypeScript changes, test verification, and delivery decisions.
Why use it?
They give a coding agent the project's constraints so it works with the existing files, tools, configuration ownership, and tests instead of applying generic assumptions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; mentions Codex; mentions OpenCode.

This is jyt6640/persona-harness's own configuration. It tells Codex and OpenCode how to work on persona-harness 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 persona-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jyt6640/persona-harness. 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/jyt6640/persona-harness/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/jyt6640/persona-harness

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 persona-harness AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jyt6640/persona-harness/agents-md/github.svg)](https://agentmods.dev/instructions/jyt6640/persona-harness/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jyt6640/persona-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/jyt6640/persona-harness/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 persona-harness AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jyt6640/persona-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/jyt6640/persona-harness/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 768 This file is loaded in full into every session.
When invoked 768 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 $0.00768 $0.00768
Opus 5 $0.00384 $0.00384
Sonnet 5 $0.00154 $0.00154
Haiku 4.5 $0.00077 $0.00077

Measured 3d ago against content hash 200c877f4919, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

persona-harness 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 3d 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 · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Persona Harness Development

Repository Context

This repository builds the Persona Harness TypeScript CLI, OpenCode runtime, portable host adapters, and shared engineering skills. The delivered backend workflow targets Java/Spring; that consumer target is not this source tree's implementation language. Read .persona/project-profile.jsonc when present. If an initialized consumer profile conflicts with the source tree, explain the conflict and use the actual files being changed to scope source maintenance. Do not bootstrap a consumer workflow merely to work on this package.

  • Keep the canonical engineering philosophy and approved project decisions useful to the task. Preserve user-owned configuration and generated-adapter ownership boundaries.
  • Inspect named source files and nearby tests. Do not use dependencies, .persona/evidence, or generated dist as implementation context.
  • Use the existing Node/npm/TypeScript/Vitest toolchain. The canonical publisher version is in package.json; do not switch package managers during a fix.

Working Agreements

  • Continue an authorized task through implementation, verification, and report. Reuse permission given for the same scope. Ask only about a material unresolved choice or a next action outside that authorization.
  • Treat side questions and corrections as steering. Explain confusion before asking another question. Stop an interview immediately when requested.
  • Skill guidance never overrides the user's task or grants new permission. Announce the selected skill once. Name an exact conflicting instruction if it blocks progress.
  • Default to the main session. Use subagents only with the user's permission; when permitted for this repository, use Luna Max only.
  • Keep edits scoped. Preserve unrelated work and use an isolated worktree when the shared checkout is dirty.

Verification

  • During implementation, use npx vitest run <affected-tests> and npm run typecheck as appropriate.
  • After changing shared skills, build and generate host plugins with npm run generate:host-plugins, then validate the generated distribution.
  • Public behavior changes need behavioral regressions. Prompt prose is reviewed directly; sentence snapshots do not prove model behavior.
  • Use one heavyweight build/test/package job at a time. Expand checks for shared behavior and the required release gates; repeat only after relevant changes or failed evidence.
  • Record actual commands and outcomes. Synthetic fixtures, installed-package checks, and live host observations prove different things.

Read the full file on GitHub · 73 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. 3d ago First seen · 73 lines · 768 tokens per session scan A 200c877f4919

Subscribe to this mod's changes

persona-harness AGENTS.md is an instructions file published in the GitHub repository jyt6640/persona-harness (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 768 tokens to every session, about $0.0038 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 2026-09-06.

Related

Other instructions, from other repositories

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

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 · 5,153 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

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens