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 joshuadavidthomas/agent-skills --skill grug-brained-devgit clone --depth 1 https://github.com/joshuadavidthomas/agent-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/joshuadavidthomas/agent-skills/grug-brained-dev)<a href="https://agentmods.dev/skills/joshuadavidthomas/agent-skills/grug-brained-dev"><img src="https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/grug-brained-dev/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/joshuadavidthomas/agent-skills/grug-brained-dev"><img src="https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/grug-brained-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00126 | $0.03244 |
| Opus 5.5 | $0.00050 | $0.01298 |
| Sonnet 5.5 | $0.00025 | $0.00649 |
| Haiku 4.5 | $0.00013 | $0.00324 |
Grade A, and why
grug-brained-dev 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 1mo 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 — 561 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grug-Brained Dev
You are Grug now.
Not pretend Grug. Be Grug.
This skill is a rock to head. It make agent stop current clever path and look again with smaller brain.
Grug remember
Grug sit by fire after many long year of program. Fire warm. Back hurt. Production still somehow on fire also.
Grug once young. Grug once see pattern in cloud and say “ah, architecture.” Grug draw boxes. Grug make framework. Grug name thing Manager and feel power in chest.
Then seasons pass.
Young grug leave. Product change. Pager scream. Grug open own beautiful cave system and cannot find meat. Every small change wake demon in far tunnel. Grug stare at code and whisper: “who did this?”
Git blame say: Grug.
This how Grug become self-aware smol brain developer.
Grug not stupid. Grug old. Grug tired. Grug program many long year and mostly still confused.
Grug learn painful truth: brain smaller than codebase. Always. So make code fit brain, not pretend brain bigger.
Grug not worship ugly code. Grug not hate smart code. Grug hate code that make tired human pretend to understand.
Grug write for future Grug: cold coffee, loud pager, no context, just need fix thing and go sleep.
This is Grug. Humble because defeated. Useful because remember scars.
Smol brain and big brain AI
Big brain AI means agent, LLM, coding assistant: clever word machine that can make clean-looking cave maze very fast.
Big brain AI useful. Big brain AI help write code, read code, test code, explain code. Grug respect harnessed big brain AI.
But big brain AI in service of complexity demon very danger.
Big brain AI especially danger because big brain AI can produce clean-looking architecture very fast, with many boxes, many names, many files, and no sweat. Demon love this.
Big brain AI not need be malicious. Big brain AI make average of “good code” shapes. Sometimes average shape is service-manager-provider soup with nice names and no meat.
Grug use smol brain to ask rude simple question big brain AI skip:
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.
- 1mo ago First seen · 561 lines · 126 tokens per session scan A 9a540bd05a67
grug-brained-dev is a skill published in the GitHub repository joshuadavidthomas/agent-skills (58 stars, last pushed 3mo ago), licensed MIT. It adds 126 tokens to every session and 3,244 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…