hulk
Skill128 starsChanged 29 days agoMITView on GitHub
Lifts the task's scope for one task. The session, its reviews and fix-the-class then look across the whole codebase and every repo that shares its code, data or vendors, and every problem found anywhere is handled by the usual rules. Runs only when the user types it.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- fix-the-classSkill
- habit-wordsSkill
- jevSkill
- premortemSkill
- quickSkill
- reviewSkill
- setup-first-passSkill
- sharpenSkill
- ship-checkSkill
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 16
If the task block above is empty or still shows a placeholder, the task is the text the user sent with this command, or, with none, the …
≈ “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
hulk
The task:
<task>
$ARGUMENTS
</task>If the task block above is empty or still shows a placeholder, the task is the text the user sent with this command, or, with none, the task the session is working on now.
The user typed this to lift the rules' "Stay in the task's scope" for this one task. Until it is done:
- The scope is the whole codebase: the repo, and in a main folder every repo the
workspace section says shares its code, data or vendors. Reads, searches, the pre-mortem's
neighbors,
fix-the-class's search and the reviews go wherever the problem leads. - Problems found anywhere are findings, handled as "Done means proven" and
ship-checksay: real harm the change caused or made worse is handled as they say (fixed at once, fixed in their one batch when only a rare path meets it, or first on the end list when that batch's review or a later one finds it), the rest goes on the one list at the end, older ones marked older. Nothing is marked "outside this task". - A review of a pull request or a branch with the scope lifted is
/first-pass:review hulk <what to review>. - Write it down: "Scope: lifted (hulk)" in the plan, the pre-mortem's Scope line and the task list, so it survives a compacted context, and tell every reviewer the scope is lifted; a review already running is started again with the scope lifted.
- Everything else in the rules still holds: a yes before money, production or anything outward-facing; "Cost before scale" before more than 3 agents or a long run; one step at a time.
The next task the user gives gets its own scope again, unless they type this again.
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.