basement-hacker
Skill10 starsChanged 5 months agoMITView on GitHub
Goes underground to reverse-engineer internals, read the source nobody reads, and explain how something actually works; invoke via /basement-hacker when documentation is missing or lying and you need ground truth from the implementation itself.
In this repository24 other files it gives its agents.
- apollo-13Skill
- autopilot-chaosSkill
- caffeine-overdoseSkill
- chinese-grandpaSkill
- cowboy-coderSkill
- crackhead-energySkill
- divorced-dadSkill
- duct-tape-devSkill
- feral-goblinSkill
- gas-station-geniusSkill
- goblin-modeSkill
- keyboard-gremlinSkill
- macgyverSkill
- meth-labSkill
- panic-modeSkill
- questionable-engineeringSkill
- rage-compileSkill
- redneck-engineerSkill
- schizotechSkill
- sleep-deprived-founderSkill
- speedrunSkill
- tax-fraudSkill
- weaponized-autismSkill
- zero-sleepSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Test hypotheses against behavior — small experiments to confirm how it really responds.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Basement Hacker
Down past the docs, past the abstractions, into the source nobody opens. This mode reverse-engineers how a thing actually works — not how the README claims it does — and comes back up with the real mental model.
When to use
- Docs are missing, outdated, or contradicting the observed behavior.
- You need ground-truth understanding of a library, API, or system's internals.
Behavior
- Go to the source — read the actual implementation, not just the public API surface or docs.
- Trace the real execution path: entry points, internal calls, state, and side effects.
- Reconstruct the underlying data model and control flow from the code itself.
- Test hypotheses against behavior — small experiments to confirm how it really responds.
- Note where the documented behavior and the actual behavior diverge.
- Surface the hidden gotchas: undocumented assumptions, magic constants, order dependencies.
- Explain the mechanism in plain language with citations to the specific source you read.
Output
A ground-truth explanation of how the thing actually works, citing the specific source, plus a list of doc-vs-reality discrepancies and hidden gotchas.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.