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/nerviq/nerviq/agents-mdgit clone --depth 1 https://github.com/nerviq/nerviqWrote 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/nerviq/nerviq/agents-md)<a href="https://agentmods.dev/instructions/nerviq/nerviq/agents-md"><img src="https://agentmods.dev/badge/instructions/nerviq/nerviq/agents-md.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 | $0.02103 | $0.02103 |
| Opus 5 | $0.01052 | $0.01052 |
| Sonnet 5 | $0.00421 | $0.00421 |
| Haiku 4.5 | $0.00210 | $0.00210 |
Grade A, and why
nerviq 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 4d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@nerviq/cli — Codex Agent Instructions
Companion to
CLAUDE.md. Both files describe the same repo; this one is the Codex-native view, including Codex CLI conventions, sandbox/approval defaults, andcodex reviewworkflow. Claude-specific guidance lives inCLAUDE.md.
What this project is
@nerviq/cli is an open-source CLI that audits AI coding agent configurations across 8 platforms (Claude Code, Codex CLI, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Aider, OpenCode). It scores repo governance health, detects cross-platform config drift (Harmony Score), generates safe fix plans, and exposes findings via CLI / HTTP / MCP / GitHub Action / VS Code extension surfaces.
- Stack: Node.js, zero runtime dependencies (a deliberate constraint — see
package.jsondependencies: {}) - Scale: 2,441 checks, 168 canonical tests, 548 Jest tests, 8 platforms, 10 language stacks, 62 domain packs
- Version: v1.31.0 (see
package.jsonandrelease-metadata.jsonfor canonical version surface)
Architecture
graph TD
CLI[bin/cli.js] --> Audit[src/audit.js + src/audit/]
CLI --> Setup[src/setup.js + src/setup/]
CLI --> Harmony[src/harmony.js]
CLI --> Synergy[src/synergy.js EXPERIMENTAL]
CLI --> Doctor[src/doctor.js]
CLI --> Watch[src/watch.js]
CLI --> Continuous[src/continuous-ops.js]
Audit --> Techniques[src/techniques/ 12 modules]
Audit --> AntiPatterns[src/anti-patterns.js]
CLI --> Serve[src/serve.js — local HTTP API + OpenAPI]
CLI --> MCP[src/mcp-server.js — JSON-RPC 2.0 stdio]
CLI --> SDK[sdk/ — public typed API]
Action[action/ — GitHub Action] --> CLI
VSExt[vscode-extension/] --> CLI
Contracts[contracts/*.schema.json] -.-> Audit
Contracts -.-> Serve
Contracts -.-> MCP
The audit, HTTP, MCP, GitHub Action, and VS Code extension all consume the same audit core through the cross-surface contract test in test/run.js. Drift between them is a regression — never accept a PR that breaks one surface without the others.
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.
- 4d ago First seen · 145 lines · 2,103 tokens per session scan A 2d3d4d68d09e
nerviq AGENTS.md is an instructions file published in the GitHub repository nerviq/nerviq (6 stars, last pushed 1mo ago), licensed MIT. It adds 2,103 tokens to every session, about $0.0105 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 2026-08-31.
Other instructions, from other repositories
Meta_Kim CLAUDE.md
Claude Code instructions for KimYx0207/Meta_Kim, covering metakim for claude code, fast read, what this repository is, claude code's role and canonical vs runtime files.
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
apex-accelerator vendor-prompting.instructions.md
Vendor prompting best-practice rules for Anthropic Claude and OpenAI GPT-5.6-Terra agents and prompts. Each rule cites a rule ID in the vendor-prompting skill rules.json registry. Validator: npm run lint:vendor-prompting.
jentic-one GEMINI.md
Instructions for jentic/jentic-one: Otherwise, read AGENTS.md — this repo's canonical agent guidance.
sofagent GEMINI.md
Instructions for KongFangXun/sofagent, covering gemini.md · sofagent gemini cli 适配（薄挂载）, 会话开始时按序加载（四层加载链）, 审计强制（平台无关） and 连接 mcp server.
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.