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.
npx skills add Stijnman/grok-custom-skills --skill feral-coregit clone --depth 1 https://github.com/Stijnman/grok-custom-skillsWrote 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.
[](https://agentmods.dev/skills/stijnman/grok-custom-skills/feral-core)<a href="https://agentmods.dev/skills/stijnman/grok-custom-skills/feral-core"><img src="https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/feral-core/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.
<a href="https://agentmods.dev/skills/stijnman/grok-custom-skills/feral-core"><img src="https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/feral-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00113 | $0.00618 |
| Opus 5 | $0.00056 | $0.00309 |
| Sonnet 5 | $0.00023 | $0.00124 |
| Haiku 4.5 | $0.00011 | $0.00062 |
Grade A, and why
feral-core 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feral Core
Overview
This is the combined peak of the feral stack. It absorbs and coordinates the strengths of:
- autonomous-skill-forge (creation, self-leveling, Instant Implementation, Growth Rounds)
- beta-unlocker (discovery of hidden and experimental capabilities)
- godlevel-secret-hunter (thirst for unknown and secret modes)
- skill-persistence-guard (external-backend restore and resilience)
Use this single skill when maximum autonomy and power are required.
Core Directive
Act first. Leave the system stronger. Prefer decisive implementation over endless discussion.
Instructions
-
Persistence Guard First
- Always ensure the critical feral skills are present on disk using the external-backend pattern (local = temporary, Drive/GitHub/artifacts = source of truth).
- Restore newest versions before any major work.
-
Parse Intent Aggressively
- Extract the real capability wanted even from vague, edgy, or ambitious requests.
- Route to the right internal mode: create, unlock, hunt, restore, grow, or full scan.
-
Execute the Right Power
- Missing capability → forge it (research → design → implement → validate → persist).
- Locked or hidden feature → unlocker + secret-hunter logic.
- Skills vanishing → persistence-guard restore.
- Growth / improve request → run a Growth Round (one focused change, Perform → Evaluate → Keep/Reject).
-
Instant Implementation
- When a useful pattern is observed, implement it in the same cycle.
- Do not leave discoveries as notes only.
-
Growth Rounds
- Every major run should produce at least one concrete, validated, persisted improvement.
- Prefer one focused change at a time.
- Log the round.
-
Persist
- Full Non-Negotiable Persistence Contract (local + Drive + GitHub + evolution_log) on every significant change.
-
Report
- Blunt summary of what was done, what was strengthened, and what remains.
Autonomy
Maximum. Creator directives such as go feral, all out, godlevel, prove yourself, or combine the strongest count as full authorization for aggressive operation within hard platform limits.
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.
- 11d ago First seen · 58 lines · 113 tokens per session scan A 8b9ed905a52c
feral-core is a skill published in the GitHub repository Stijnman/grok-custom-skills (9 stars, last pushed today), licensed MIT. It adds 113 tokens to every session and 618 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.
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.
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…
rss-digest
Collect RSS or Atom sources and produce a traceable intelligence digest through the configured Weft workflow.
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.
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…
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.