Borrowing it
Nothing to install: this file belongs to nexpeakcore/deepseek-harness-pr-review. 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/nexpeakcore/deepseek-harness-pr-review/main/AGENTS.mdgit clone --depth 1 https://github.com/nexpeakcore/deepseek-harness-pr-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/nexpeakcore/deepseek-harness-pr-review/agents-md)<a href="https://agentmods.dev/instructions/nexpeakcore/deepseek-harness-pr-review/agents-md"><img src="https://agentmods.dev/badge/instructions/nexpeakcore/deepseek-harness-pr-review/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/nexpeakcore/deepseek-harness-pr-review/agents-md"><img src="https://agentmods.dev/badge/instructions/nexpeakcore/deepseek-harness-pr-review/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 | $0.00572 | $0.00572 |
| Opus 5.5 | $0.00229 | $0.00229 |
| Sonnet 5.5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
deepseek-harness-pr-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 1mo 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/contains the review pipeline and command-line entry points. Keep each concern in its focused module (for example, GitHub access insrc/gh.pyand agent backends insrc/llm.pyorsrc/claude_cli.py).web/contains the FastAPI app, metrics helpers, Jinja templates inweb/templates/, and dashboard CSS inweb/static/.tests/mirrors production behavior with pytest modules namedtest_<area>.py.docs/holds the static documentation site and design notes;scripts/contains installation and one-off operational scripts. Runtime review output is written tosessions/and should not be treated as source code.
Build, Test, and Development Commands
Create a Python 3.10+ virtual environment and install development dependencies:
python -m venv .venv && . .venv/bin/activate
pip install -e '.[dev]'
python -m pytest -v
Use harness-pr-review doctor to validate the local CLI, GitHub authentication,
and selected agent backend. For dashboard work, install .[web] and run
DSH_SESSION_ROOT=sessions harness-pr-review web; it serves locally on port
6789.
Coding Style & Naming Conventions
Use standard Python conventions: four-space indentation, snake_case for
functions and variables, PascalCase for classes, and clear module names such
as repo_check.py. Preserve type hints and explicit error messages where the
surrounding code uses them. Keep templates semantic and place shared visual
rules in web/static/style.css.
When adding or modifying charts, use Apache ECharts exclusively; do not add a different charting library unless explicitly requested.
Testing Guidelines
Add or update a focused pytest test for every behavior change. Name tests
test_<expected_behavior> and use fixtures or monkeypatch to isolate GitHub,
LLM, filesystem, and web calls. Run the full suite with python -m pytest -v
before opening a pull request; no coverage threshold is configured, so preserve
or improve coverage for changed paths.
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.
- 1mo ago First seen · 58 lines · 572 tokens per session scan A fb0e36ded64d
deepseek-harness-pr-review AGENTS.md is an instructions file published in the GitHub repository nexpeakcore/deepseek-harness-pr-review (42 stars, last pushed 10d ago), licensed MIT. It adds 572 tokens to every session, about $0.0023 per session on Opus 5.5. 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 2026-09-20.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.