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 agentmods add skills/superhero-tech/super-brain/querynpx skills add superhero-tech/super-brain --skill querygit clone --depth 1 https://github.com/superhero-tech/super-brainWhat 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 | $0.00056 | $0.00897 |
| Opus 5 | $0.00028 | $0.00449 |
| Sonnet 5 | $0.00011 | $0.00179 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
query 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 2d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Query
Answer from the wiki, not from memory, and keep the answer so the next question starts further along.
Write the answer and every file you produce in the language the human is using.
How to invoke
- Any question the vault plausibly covers
- "What do we know about X?"
- "Compare X and Y from what I have"
- "Write me a briefing on X"
/query
How it works
1. Find the pages
Read 4-Knowledge/index.md first. It is the map, and it exists so you do not have to read every page to find three.
Pick the pages that bear on the question, entity pages included when the question names a person, company or tool.
If the index promises a page that is not on disk, or you find a page the index never lists, tell the human. Both are real findings.
2. Read them
Read the pages you picked, in full. Follow [[links]] one hop out when the question sits between two topics.
3. Answer
Cite every claim with [source: page-name.md], naming the wiki page you actually read.
Where the wiki disagrees with itself, show both sides and name the sources. A > CONTRADICTION: marker is a finding to surface, not noise to smooth over.
Where the wiki is thin, say so in the answer. If you add something from outside the vault, mark it plainly as outside knowledge so the human can tell the two apart.
4. Save the output
Write 9-Outputs/[YYYY-MM-DD]-[short-slug].md:
---
question: [the question, as asked]
date: [YYYY-MM-DD]
pages: [wiki pages used]
filed_back: [page name, or: no]
---
# [Question as a title]
[The answer, with [source: page-name.md] citations]
## What this is built on
- [[Page A]] - what it contributed
- [[Page B]] - what it contributed
## Gaps
[What the wiki could not answer. The most useful section in the file: it tells
the human what to read next.]
A one-line lookup does not need a file. Say out loud that you skipped it, so the human knows this answer was not kept.
When the answer has a shape that prose flattens - a comparison across dimensions, a timeline, a distribution - offer the better format and save it beside the markdown under the same slug. The format rules are in 8-System/brain.md under Conventions.
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.
- 2d ago First seen · 94 lines · 56 tokens per session scan A 0aaa25d1d6d1
query is a skill published in the GitHub repository superhero-tech/super-brain (106 stars, last pushed 7d ago), licensed MIT. It adds 56 tokens to every session and 897 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…