agentmods.dev

skillsmith AGENTS.md

skillsmith AGENTS.md is an instructions file for Codex, OpenCode from ApexIQ/skillsmith. It costs 1,377 tokens per session, scanned A, original, MIT.

A set of instructions for AI coding assistants working on the skillsmith project, including required context, development stages, branching guidance, and slash commands.

In plain words
What is it for?
Use it to guide repository changes, choose relevant skills, follow the seven-stage development cycle, and verify completed work.
Why use it?
It keeps different assistants aligned with the project's architecture and working practices.

Instructions file for CodexOpenCode

not rated 5 5mo ago A scan 1,377 tokens original MIT
View the source file ApexIQ/skillsmith
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/apexiq/skillsmith/agents-md
Clone the repo
git clone --depth 1 https://github.com/ApexIQ/skillsmith

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 skillsmith AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/apexiq/skillsmith/agents-md.svg)](https://agentmods.dev/instructions/apexiq/skillsmith/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/apexiq/skillsmith/agents-md"><img src="https://agentmods.dev/badge/instructions/apexiq/skillsmith/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,377 This file is loaded in full into every session.
When invoked 1,377 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 $0.01377 $0.01377
Opus 5 $0.00688 $0.00688
Sonnet 5 $0.00275 $0.00275
Haiku 4.5 $0.00138 $0.00138

Measured yesterday against content hash fb8687aaa0b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skillsmith 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 yesterday.

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 · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Primary project instructions for AI coding agents.

1. Prime Directives

  1. Read AGENTS.md and .agent/STATE.md first.
  2. Read .agent/lessons.md for long-term project memory and past mistakes.
  3. Read .agent/principles/CORE_PRINCIPLES.md for project behavioral rules.
  4. Read .agent/project_profile.yaml and .agent/context/project-context.md before making stack assumptions.
  5. Search .agent/skills/ for the most relevant instructions before implementation.
  6. Follow the 7-Stage Workflow: Discover → Plan → Build → Review → Test → Ship → Reflect.
  7. AND/OR Thinking: Treat every goal as a root node in a dynamic Thinking Tree. If Strategy A fails, prune it and branch to Strategy B (OR) at the exact failure node.
  8. Update .agent/STATE.md after significant steps.

2. The 7-Stage Development Cycle

Stage Objective
Discover Audit profile, context, and code for constraints.
Plan Define minimal patch with verification points.
Build Implement atomic changes in isolation.
Review Adversarial check for risks and regressions.
Test Identify highest-risk behavior and verify.
Ship Generate clean handoff with evidence.
Reflect Record lessons and update project state.

3. Execution Standard

  • Plan first for non-trivial work (3+ steps, architecture changes, migrations, or risky edits).
  • Keep fixes minimal and focused. Avoid broad refactors unless required for correctness.
  • Delegate to subagents only for parallelizable or clearly specialized tasks.
  • One owner per subtask; merge results only after verification.
  • Never mark done without evidence (tests, command output, or concrete behavioral checks).

4. Slash Command Registry (MCP Mapping)

This project supports specialized engineering commands. If the user invokes them, use the corresponding MCP tool:

  • /autonomous -> Use autonomous_mission
  • /audit, /security, /performance -> Use audit_repository
  • /explain -> Use explain_code
  • /verify -> Use verify_readiness
  • /review -> Use review_changes
  • /sync -> Use sync_project

Read the full file on GitHub · 139 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. yesterday First seen · 139 lines · 1,377 tokens per session scan A fb8687aaa0b6

Subscribe to this mod's changes

skillsmith AGENTS.md is an instructions file published in the GitHub repository ApexIQ/skillsmith (5 stars, last pushed 5mo ago), licensed MIT. It adds 1,377 tokens to every session, about $0.0069 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 2026-09-03.

Building agentsagentic-aiai-agentsai-coding-assistantai-developer-toolscli-toolcontext-management
Related

Other instructions, from other repositories

mex CLAUDE.md

Claude Code instructions for mex-memory/mex, a project described as: Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.

mex-memory/mex · 205 tokens

mex AGENTS.md

AGENTS.md instructions for mex-memory/mex, a project described as: Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.

mex-memory/mex · 205 tokens

automate CLAUDE.md

Claude Code instructions for kobiton/automate, covering claude.md, getting started, commands, single test file and architecture.

kobiton/automate · 5,785 tokens

ccRecall CLAUDE.md

Claude Code instructions for tznthou/ccRecall, covering ccrecall — ai memory service for claude code, 定位, 指令, 技術約束 and 架構.

tznthou/ccRecall · 948 tokens

automate AGENTS.md

AGENTS.md instructions for kobiton/automate, covering kobiton automate - agent guide, what this plugin does, userintent format, getting started (new users) and routing ambiguous prompts.

kobiton/automate · 5,337 tokens

sumulige-claude AGENTS.md

AGENTS.md instructions for sumulige/sumulige-claude, covering agents.md - agent 系统详解, technical co-founder working agreement (always-on), layer 1: 什么是 agent？ (5 分钟), 最简单的解释 and 类比：餐厅团队.

sumulige/sumulige-claude · 6,196 tokens