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.
curl -O https://raw.githubusercontent.com/jyt6640/persona-harness/main/AGENTS.mdgit clone --depth 1 https://github.com/jyt6640/persona-harnessWrote 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/jyt6640/persona-harness/agents-md)<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.
<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>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 | $0.00768 | $0.00768 |
| Opus 5 | $0.00384 | $0.00384 |
| Sonnet 5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
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.
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 generateddistas 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>andnpm run typecheckas 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.
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.
- 3d ago First seen · 73 lines · 768 tokens per session scan A 200c877f4919
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.
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.
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 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).
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.
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.