forge-skills AGENTS.md

forge-skills AGENTS.md is an instructions file for Codex, OpenCode from aneja5/forge-skills. It costs 3,107 tokens per session, scanned A, original, MIT.

Project instructions for Forge Skills, a collection of structured workflows that coding agents invoke for different kinds of engineering work. They map tasks such as requirements, API design and database design to specific skills with verification checks.

In plain words
What is it for?
Selecting skills for a task, following their required steps and verifying work before considering it complete.
Why use it?
They help agents choose the right workflow and prevent unfinished or unchecked implementation work.

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/aneja5/forge-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/aneja5/forge-skills

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 forge-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aneja5/forge-skills/agents-md.svg)](https://agentmods.dev/instructions/aneja5/forge-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/aneja5/forge-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/aneja5/forge-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,107 This file is loaded in full into every session.
When invoked 3,107 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 $0.03107 $0.03107
Opus 5 $0.01554 $0.01554
Sonnet 5 $0.00621 $0.00621
Haiku 4.5 $0.00311 $0.00311

Measured 4d ago against content hash 599162e3e0aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forge-skills 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 · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Forge Skills for AI coding agents. Skills encode structured engineering workflows — not reference docs. Every skill has a trigger, a process, and a verification gate.

Core Rules

  • If a task matches a skill, invoke the skill before doing anything else
  • Skills are in skills/<name>/SKILL.md
  • Never implement directly when a skill applies
  • Follow skill steps in order — do not skip steps
  • A task is not complete until the skill's Verification checklist passes
  • Every skill ships with pressure-scenario tests in tests/<name>/ (see tests/METHODOLOGY.md)

Intent → Skill Mapping

Grouped by lifecycle phase.

Define & specify

Raw idea / haven't thought it through    →  idea-griller
Write a spec / PRD / requirements        →  spec-driven-development

Design

Establish brand foundations / voice      →  brand-and-identity
Design system / write contracts          →  architecture-and-contracts
Design REST endpoints / API contracts    →  api-design
Design schema / migrations               →  database-design
Establish design tokens / component lib  →  design-system
Build a component catalog                →  component-library
Define page templates + responsive plan  →  page-composition
Build charts / dashboards / data display →  data-visualization
Decide modal vs sheet, expand vs nav     →  interaction-patterns

Validate before building

Research competitors / positioning       →  competitive-analysis
Plan go-to-market / find customers       →  gtm-strategy
Will this scale / capacity math          →  scalability-analysis
Security & compliance review             →  security-and-compliance
Validate decisions externally            →  cross-validation

Plan & build

Break into tasks / sprint plan           →  planning-and-task-breakdown
Implement code / execute tasks           →  incremental-implementation
Need test-first discipline               →  tdd
Define test pyramid + coverage targets   →  testing-strategy
Run multiple agents in parallel          →  parallel-execution-strategy
Need realistic demo / test data          →  seed-data-and-fixtures

Read the full file on GitHub · 277 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 · 277 lines · 3,107 tokens per session scan A 599162e3e0aa

Subscribe to this mod's changes

forge-skills AGENTS.md is an instructions file published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 3,107 tokens to every session, about $0.0155 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.