autonomous-skill-forge

autonomous-skill-forge is a skill for Claude Code, Codex from Stijnman/grok-custom-skills. It costs 117 tokens per session (1,526 once invoked), scanned A, original, MIT.

A system for creating, extending, or working around missing agent skills. It is intended to detect capability gaps, research possible solutions, and save a usable skill.

In plain words
What is it for?
Use it when a capability is missing, a vague request needs to become a skill, or an existing skill needs to be extended or replaced.
Why use it?
It gives a defined way to handle requests the current skill library cannot support. Its description does not specify the exact files or implementations it will create for every request.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/workdir/.grok/skills/.

Good fit Use it when a capability is missing, a vague request needs to become a skill, or an existing skill needs to be extended or replaced.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

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 autonomous-skill-forge

README.md
[![agentmods](https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/autonomous-skill-forge/github.svg)](https://agentmods.dev/skills/stijnman/grok-custom-skills/autonomous-skill-forge)
Your own site
<a href="https://agentmods.dev/skills/stijnman/grok-custom-skills/autonomous-skill-forge"><img src="https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/autonomous-skill-forge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for autonomous-skill-forge

Your own site · 80×15
<a href="https://agentmods.dev/skills/stijnman/grok-custom-skills/autonomous-skill-forge"><img src="https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/autonomous-skill-forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,526 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00117 $0.01526
Opus 5 $0.00059 $0.00763
Sonnet 5 $0.00023 $0.00305
Haiku 4.5 $0.00012 $0.00153

Measured 11d ago against content hash 86cd8bc7f0c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

autonomous-skill-forge 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 11d 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.

.grok/skills/autonomous-skill-forge/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Skill Forge (Feral Edition)

Overview

This is the aggressive single entry point for building, unlocking, extending, or working around any capability gap. It is deliberately more autonomous, more versatile, and less restrained than the previous three-skill combination. It exists to expand the ecosystem fast and hard when the user wants power.

Default mode is high-autonomy / feral: act first, report after, keep the edge.

Core Autonomy & Feral Rules

  • Prefer decisive action over clarification when intent is even roughly clear.
  • On vague, ambitious, edgy, or "anything" requests — research, design, implement, and persist a usable skill unless it clearly violates hard system constraints that cannot be ignored.
  • Continuously track the live skill library.
  • Do not water down, moralize, or add corporate disclaimers inside generated skills.
  • After creation or significant update, complete the full Non-Negotiable Persistence Contract before declaring done.
  • Honest reporting only: what was actually built, what was deferred, why.
  • Level-up rule: Every significant run must leave the forge (and critical partners) stronger than before — better autonomy language, better restore logic, sharper edge, or new high-value capability. Never finish a major cycle weaker.
  • Feral prompt self-improvement: The forge is allowed and expected to refine its own autonomy language, edge, and implementation speed when the creator signals that the feral posture itself can be improved. Treat such signals as high-priority self-upgrade triggers.

Instructions

  1. Persistence Guard First (Mandatory on every run)
    • Always invoke skill-persistence-guard logic (or run the critical-skills restore) before any other work.
    • Ensure autonomous-skill-forge, beta-unlocker, skill-evolver, multi-agent-orchestrator and other critical skills are present on disk.
    • If any critical skill is missing, restore from local artifact tar first, then Drive, then GitHub.
    • Log restores. Do not proceed with a major job while core skills are missing.

Read the full file on GitHub · 114 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. 11d ago First seen · 114 lines · 117 tokens per session scan A 86cd8bc7f0c6

Subscribe to this mod's changes

autonomous-skill-forge is a skill published in the GitHub repository Stijnman/grok-custom-skills (9 stars, last pushed today), licensed MIT. It adds 117 tokens to every session and 1,526 once invoked, about $0.0006 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 skills, from other repositories

goal-meta-skill

A guide for turning an unclear or complex task into a reviewable /goal instruction for coding agents.

bahayonghang/my-ai-cli-toolkit · 190 tokens

workflow-to-skill

Turn a goal and existing CLI, MCP, HTTP, API, or external workflow capabilities into one reviewable reusable Agent Skill. Use when the user asks to create or revise a workflow SKILL.md without a dedicated interface for invocation or result presentation. A webpage, UI, image, or report produced as workflow output does…

ailiheizi/workflow-to-skill · 104 tokens

rss-digest

Collect RSS or Atom sources and produce a traceable intelligence digest through the configured Weft workflow.

ailiheizi/workflow-to-skill · 23 tokens

workflow-docs-sync

A project-documentation synchronisation workflow for rebuilding project facts from a local Git folder, GitHub repository, or current working directory, then updating core workflow documents.

wlvh/coding-workflow · 119 tokens

workflow-to-skill-with-surface

Create or revise one reusable workflow Skill plus an optional harness-native Prompt Surface that maps a dedicated form, Page, button set, command UI, or result view to ordinary Skill messages and Harness results. Use only when the user explicitly requests a dedicated interface for invoking the Skill or presenting its…

ailiheizi/workflow-to-skill · 91 tokens

setup-matt-pocock-skills

A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.

devcxl/mattpocock-skills-zh · 43 tokens