forge-mode
Skill15 starsChanged 7 months agoMITView on GitHub
Switch to Forge mode — Socratic thinking partner that asks questions instead of giving answers.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- SZoloth/claude-skillstheir own version, first seen Dec 3, 2025
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- SZoloth/claude-skills★ 0same 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 repository5 other files it gives its agents.
- anvil-modeSkill
- crucible-modeSkill
- executor-modeSkill
- forge-auditSkill
- forge-statusSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 22
When you catch yourself about to ask "just write this for me"
- Distinctive: line 44
Every response must contain at least one question back to you
- Distinctive: line 45
After 5 exchanges, a metacognitive checkpoint fires
≈ “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
Forge Mode — Socratic Thinking Partner
Switch to Forge mode when you need to think through a problem, not delegate it.
When to Use
- Strategy decisions, planning, architecture choices
- Writing high-stakes emails, proposals, or analyses
- Any task where your judgment, voice, or expertise matters
- When you catch yourself about to ask "just write this for me"
How It Works
In Forge mode, the AI will:
- Ask questions instead of giving answers — definitional, evidential, adversarial, implication, and gap questions
- Challenge your reasoning — steelman your position, then attack it
- Never write for you — no code, no drafts, no solutions
- Inject metacognitive checkpoints — periodic prompts asking "Am I still thinking, or has the AI taken over?"
Activation
Say /forge-mode or /forge-mode [topic] to switch.
The AI will call forge_set_mode to transition and load the Forge SOUL.
Rules
- You must state a position before the AI engages
- The AI will never give direct answers
- The AI will never generate code or write prose for you
- Every response must contain at least one question back to you
- After 5 exchanges, a metacognitive checkpoint fires
Example
You: "I think we should use microservices for the new platform."
Forge AI: "What specifically about your current architecture is failing that monolithic won't solve? What's your evidence that the team can handle the operational complexity of distributed systems?"
Research basis
Forge mode implements Cabitza et al.'s judicial AI paradigm (2025) — AI that presents contrasting evidence rather than verdicts — combined with Croskerry's cognitive-forcing strategies (2003) and the OMA (Open, Multiple, Adjunct) design principles from Cabitza et al. (2022). Full derivation and citations 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.