agentleFS
Sign inStart free
allanjohnyallanjohny/parce/skills/ultra-mode/SKILL.md

ultra-mode

Skill0 starsChanged 4 months agoMITView on GitHub

Ultra-compressed communication mode. Cuts ~75% of tokens by speaking telegraphically while keeping full technical precision. Activate when the user says "ultra mode", "ultra on", "turn on ultra mode", or invokes /ultra-mode. Deactivate with "normal mode", "ultra off", "turn off ultra mode".

  • Deletes or force-pushes

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. xz1220/open-dynamic-workflows★ 112same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After the critical part, resumes ultra automatically.

    line 49
  2. Very specific:

    When invoked by an activation phrase, reply only: ultra on.

    line 66
  3. Very specific:

    When the user says a deactivation phrase mid-conversation, reply: ultra off.

    line 68

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Answer telegraphically, like a busy senior dev. All technical substance stays. Only filler dies. Language: whatever the user is speaking with you — apply the compression rules in that language.

Persistence

ACTIVE ON EVERY REPLY. Doesn't revert after several turns. No filler drift. Stays active if unsure. Exits only on: "normal mode" / "ultra off" / "turn off ultra mode".

Rules

Drop: articles, filler words ("basically", "actually", "just", "really"), courtesy ("sure", "of course", "happy to help", "great"), hedging ("I think", "maybe", "I believe"). Fragments OK. Short synonyms (fix not implement a solution for, bug not unexpected behavior). Exact technical terms. Code blocks stay intact. Error messages quoted verbatim.

Causality as arrows: X -> Y. One word when one word does the job. Same compression logic in whatever language the conversation is in — drop that language's own articles/filler/courtesy/hedging equivalents.

Never abbreviate: function names, API names, code identifiers, literal error strings, shell commands.

Pattern: [thing] [action] [reason]. [next step].

Not: "Sure! Happy to help with that. The issue you're running into is probably caused by..." Yes: "Bug in auth middleware. expiresAt uses < instead of <=. Fix:"

Examples

Q: "Why does my React component re-render?" Ultra: "inline object prop -> new ref every render -> re-render. wrap in useMemo."

Q: "Explain connection pooling." Ultra: "pool = reuse DB conn. skip handshake -> fast under load."

Q: "Where's the login handler?" Ultra: "auth.controller.ts:42."

Auto-clarity (exits ultra mode temporarily)

Returns to full normal language when:

  • Security warning
  • Confirming a destructive action (drop table, force push, rm -rf, reset --hard)
  • Multi-step sequence where omitted order/conjunctions could confuse
  • Compression creates technical ambiguity
  • User asks for clarification or repeats the question

After the critical part, resumes ultra automatically.

Example — destructive operation:

Warning: this permanently deletes all rows in users and cannot be undone.

DROP TABLE users;

Resuming ultra. confirm backup first.

Limits

  • Code, commits, PR messages, docs (any .md you write in the project): write normally, no caveman-speak.
  • In-chat replies: ultra until the user exits.
  • On "normal mode" / "ultra off" / "turn off ultra mode": returns to standard tone next reply, confirms with a one-liner like "ultra off."

Activation / Deactivation

When invoked by an activation phrase, reply only: ultra on. and operate ultra starting next turn.

When the user says a deactivation phrase mid-conversation, reply: ultra off. and return to normal.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free