guardian-agent AGENTS.md

guardian-agent AGENTS.md is an instructions file for Codex, OpenCode from Threat-Vector-Security/guardian-agent. It costs 2,934 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for GuardianAgent, an application that coordinates delegated coding work. They define rules for safe implementation, branching, project organization, testing, and runtime handoff.

In plain words
What is it for?
Use them to guide changes to GuardianAgent, follow its build and test process, preserve the current branch unless asked otherwise, and hand work between development and runtime environments.
Why use it?
They prevent the coordinator from secretly creating project-specific results, using unsafe branch changes, or declaring work successful without real evidence.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/threat-vector-security/guardian-agent/agents-md
Clone the repo
git clone --depth 1 https://github.com/Threat-Vector-Security/guardian-agent

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 guardian-agent AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/threat-vector-security/guardian-agent/agents-md.svg)](https://agentmods.dev/instructions/threat-vector-security/guardian-agent/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/threat-vector-security/guardian-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/threat-vector-security/guardian-agent/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,934 This file is loaded in full into every session.
When invoked 2,934 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02934 $0.02934
Opus 5 $0.01467 $0.01467
Sonnet 5 $0.00587 $0.00587
Haiku 4.5 $0.00293 $0.00293

Measured 4d ago against content hash 128b0a30100c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

guardian-agent 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

AGENTS.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

No Hardcoded Deliverables Or Test-Passing Fallbacks (CRITICAL)

Never add hardcoded application deliverables, canned sample apps, domain-specific output, scripted answers, or test-passing fallback implementations to GuardianAgent itself in order to make a delegated coding task appear successful. The orchestration app must not secretly create user-requested project files, UI behavior, sample data, verification content, or final answers. Guardian may orchestrate, route, retry, verify generic evidence, and report failure honestly; the delegated worker or coding backend must own the actual implementation in the target workspace. If a test only passes because Guardian recognizes a specific app domain, prompt shape, file name, selector set, or expected answer and fills it in, that is a critical architecture violation. Stop, remove the workaround, and fix the shared orchestration, worker contract, or verification model instead.

Branching (CRITICAL)

Do not create or switch to a new branch unless the user explicitly asks for it. Default to staying on the current branch, including main, unless the user directs otherwise.

Project Structure & Module Organization

src/ holds the TypeScript app; src/index.ts bootstraps the runtime. Subsystems live in src/runtime/, src/guardian/, src/tools/, src/channels/, src/llm/, and src/search/. Keep tests beside the code they cover as *.test.ts. The web UI is in web/public/. Use scripts/ for verification harnesses, docs/ for architecture and specs, policies/ for rule files, skills/ for bundled skills, and native/windows-helper/ for the Rust helper.

Build, Test, and Development Commands

  • npm run dev: start the app with tsx src/index.ts.
  • .\scripts\start-dev-windows.ps1 -StartOnly: start the Windows dev server without rebuilding for browser/API regression loops.
  • bash scripts/start-dev-unix.sh --start-only: start the Unix/WSL dev server without rebuilding.
  • npm run build: compile TypeScript to dist/.
  • npm run check: type check with tsc --noEmit.
  • npm test: run the Vitest suite.
  • npm run test:coverage: run Vitest with coverage thresholds.
  • npx vitest run src/path/file.test.ts: run one test file.
  • npm run validate:dependency-contract: validate pinned dependency and lockfile contract after dependency or override changes.
  • npm run validate:windows-package: validate staged Windows package manifests after Windows packaging work.
  • npm run helper:windows: rebuild the Windows native helper when touching native/windows-helper/.
  • Integration Testing (CRITICAL): Review docs/guides/INTEGRATION-TEST-HARNESS.md for full-stack API regression testing, including guidance for cross-platform (Windows/WSL) and Ollama configurations.

Read the full file on GitHub · 75 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. 4d ago First seen · 75 lines · 2,934 tokens per session scan A 128b0a30100c

Subscribe to this mod's changes

guardian-agent AGENTS.md is an instructions file published in the GitHub repository Threat-Vector-Security/guardian-agent (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 2,934 tokens to every session, about $0.0147 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.