executor-mode
Skill15 starsChanged 7 months agoMITView on GitHub
Switch to Executor mode — normal AI operation with no cognitive friction. Use for mechanical tasks.
In this repository5 other files it gives its agents.
- anvil-modeSkill
- crucible-modeSkill
- forge-auditSkill
- forge-modeSkill
- forge-statusSkill
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 35
If you catch yourself using Executor mode for tasks that require your voice, judgment, or expertise — switch to Forge, Anvil, or Crucible …
≈ “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
Executor Mode — Standard AI Operation
Switch to Executor mode for mechanical tasks that don't require your judgment.
When to Use
- Formatting, translation, data transformation
- Boilerplate code generation
- Calendar coordination, scheduling
- Summarizing documents you've already read
- Any task where delegation is appropriate
How It Works
Executor mode is standard AI behavior — no friction, no questioning, no checkpoints. The AI does exactly what you ask.
Activation
Say /executor-mode to switch.
When NOT to Use
If you catch yourself using Executor mode for tasks that require your voice, judgment, or expertise — switch to Forge, Anvil, or Crucible instead. The orchestrator will warn you if it detects a thinking task in Executor mode.
Rules
- No input requirements
- No output restrictions
- No metacognitive checkpoints
- Full automation — the AI writes, generates, formats freely
Research basis
Executor mode is the only context where the Rams (AI-first) protocol from Cabitza et al. (2023) is acceptable. Rams causes anchoring and automation bias when judgment is involved — for mechanical tasks those biases are irrelevant because there's no judgment to corrupt. If you catch yourself using Executor for a task that carries your voice (an email, an argument, a design choice), switch modes. Full derivation in RESEARCH.md.
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.