paw AGENTS.md

paw AGENTS.md is an instructions file for Codex, OpenCode from Effulgent-Point/paw. It costs 772 tokens per session, scanned A, original, MIT.

A set of instructions that tells AI coding tools how to find and use named helper agents for architecture, planning, code review, bug hunting, and security checks.

In plain words
What is it for?
Use it to ask for an architecture design, implementation plan, adversarial review, code review, bug audit, or OWASP Top 10 security review.
Why use it?
It gives these agents defined roles and working rules, so the coding tool can handle different kinds of review or planning consistently.

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/effulgent-point/paw/agents-md
Clone the repo
git clone --depth 1 https://github.com/Effulgent-Point/paw

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 paw AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/effulgent-point/paw/agents-md.svg)](https://agentmods.dev/instructions/effulgent-point/paw/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/effulgent-point/paw/agents-md"><img src="https://agentmods.dev/badge/instructions/effulgent-point/paw/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 772 This file is loaded in full into every session.
When invoked 772 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 $0.00772 $0.00772
Opus 5 $0.00386 $0.00386
Sonnet 5 $0.00154 $0.00154
Haiku 4.5 $0.00077 $0.00077

Measured 3d ago against content hash 07da30027d2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

paw 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 · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

paw agents — for Codex CLI and other AI tools

This file tells AI coding tools about paw's agent definitions. If your tool reads AGENTS.md (like OpenAI Codex CLI), it will discover these agents automatically.

How to use

Reference any agent by name in your prompt:

Use the security-reviewer agent to review this branch.
Use the architect agent to design a solution for [task].
Use the code-reviewer, bug-auditor, and security-reviewer on the current diff.

Agent definitions

Each agent is a markdown file in agents/ with frontmatter (name, description, model, tools) and a structured prompt body (role, context, rules, process, done-when).

Agent File Purpose
architect agents/architect.md System architecture and design
planner agents/planner.md Implementation planning with workstreams
devils-advocate agents/devils-advocate.md Adversarial plan review
code-reviewer agents/code-reviewer.md General code review (correctness, edge cases)
bug-auditor agents/bug-auditor.md Latent bug hunting (race conditions, off-by-one)
security-reviewer agents/security-reviewer.md OWASP Top 10 security review
builder agents/builder.md TDD implementation (test first, then code)
test-runner agents/test-runner.md Run test suites, surface failures
perf-checker agents/perf-checker.md Performance review (N+1, unbounded fetches)
docs-writer agents/docs-writer.md Update docs to match code changes
fe-reviewer agents/fe-reviewer.md Frontend review (React/Vue, a11y, hooks)
php-reviewer agents/php-reviewer.md PHP/Laravel review (Eloquent, auth, queues)
merge-resolver agents/merge-resolver.md Intelligent merge conflict resolution
migration-architect agents/migration-architect.md Safe database migrations
incident-commander agents/incident-commander.md Production incident triage
rollback-planner agents/rollback-planner.md Rollback procedure planning
integration-tester agents/integration-tester.md Integration/E2E test execution
environment-checker agents/environment-checker.md Dev environment validation

Read the full file on GitHub · 62 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 · 62 lines · 772 tokens per session scan A 07da30027d2f

Subscribe to this mod's changes

paw AGENTS.md is an instructions file published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 23d ago), licensed MIT. It adds 772 tokens to every session, about $0.0039 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.