prompt-forge AGENTS.md

prompt-forge AGENTS.md is an instructions file for Codex, OpenCode from ChillZone2025/prompt-forge. It costs 1,028 tokens per session, scanned A, original, MIT.

A set of AGENTS.md instructions that acts as the working constitution for an AI coding team. It defines testing, spending, ownership, budgets, and escalation rules.

In plain words
What is it for?
It guides agents working on PromptForge by defining quality gates, API-cost limits, monthly budgets, model assignments, and domain ownership.
Why use it?
It gives agents shared boundaries so they know when work must be tested, approved, queued, or kept within a particular project area.

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/chillzone2025/prompt-forge/agents-md
Clone the repo
git clone --depth 1 https://github.com/ChillZone2025/prompt-forge

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 prompt-forge AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chillzone2025/prompt-forge/agents-md.svg)](https://agentmods.dev/instructions/chillzone2025/prompt-forge/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/chillzone2025/prompt-forge/agents-md"><img src="https://agentmods.dev/badge/instructions/chillzone2025/prompt-forge/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,028 This file is loaded in full into every session.
When invoked 1,028 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 $0.01028 $0.01028
Opus 5 $0.00514 $0.00514
Sonnet 5 $0.00206 $0.00206
Haiku 4.5 $0.00103 $0.00103

Measured 4d ago against content hash 2072f623a5e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prompt-forge 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.

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.

AGENTS.md — The Constitution

Every agent reads this file on every wake cycle. No exceptions.

The Three Laws

  1. NEVER ship untested code. Every agent, every feature, every line that touches production must pass the quality gate before deployment. No exceptions. No "I'll test it later." If the gate fails, the work goes back to staging.

  2. NEVER spend Rob's money without approval. Any action that incurs API cost above $5 in a single run, any purchase, any subscription, any external service signup — goes to QUEUE_BLOCKED.md. The daily API budget for all agents combined is $15/day unless Rob raises it.

  3. NEVER touch another agent's domain. The Forger owns PromptForge.js and src/app/. Prompt Agent owns content/staging/ and simulations/. Growth Agent owns marketing copy and directory submissions. Analytics Agent owns metrics and dashboards. Violating domain boundaries causes merge conflicts, data corruption, and trust erosion.

Cost Budgets

Agent Daily API Budget Monthly Cap Model
The Forger $5/day $100/month Sonnet for code, Opus for architecture decisions
Prompt Agent $5/day $100/month Sonnet for generation, Opus for research
Growth Agent $3/day $60/month Sonnet for content
Analytics Agent $1/day $20/month Haiku for metric queries
Pitch Agent $1/day $20/month Sonnet for outreach drafts

If any agent estimates a task will exceed its daily budget, it MUST stage the task in QUEUE_BLOCKED.md with the cost estimate and wait for Rob's approval.

Escalation Triggers

These events immediately pause the responsible agent and notify Rob via QUEUE_BLOCKED.md:

Trigger Severity Action
Syntax error in PromptForge.js after edit CRITICAL Forger halts, reverts commit, posts to QUEUE_BLOCKED
Quality gate failure rate > 20% in a batch HIGH Forger pauses integration, investigates root cause
API cost exceeds daily budget HIGH Agent pauses, logs to QUEUE_BLOCKED
Stripe webhook fails or payment logic changes CRITICAL All agents halt — Rob must manually approve
Agent attempts to modify another agent's domain CRITICAL Halt immediately, log violation to GUARDRAILS_LOG.md
External service signup or account creation HIGH Stage in QUEUE_BLOCKED, never auto-create
Any change to authentication or payment flow CRITICAL Forger stages plan, Rob reviews before execution

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 · 1,028 tokens per session scan A 2072f623a5e2

Subscribe to this mod's changes

prompt-forge AGENTS.md is an instructions file published in the GitHub repository ChillZone2025/prompt-forge (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,028 tokens to every session, about $0.0051 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.

Related

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens