Skip to content
Agentmart
Submit a tool

counterfactual-fork

Generate bounded, decision-changing alternatives for plans, diagnoses, architectures, and strategic conclusions.

Skill by serhiipriadko2-sys

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/serhiipriadko2-sys-counterfactual-fork

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Generate bounded, decision-changing alternatives for plans, diagnoses, architectures, and strategic conclusions. Use when the result may depend on an uncertain premise, future condition, adversarial actor, timing, permission, scale, or causal interpretation. Produce at most three branches: baseline, strongest credible alternative, and failure/adversarial case. For each state the changed premise, predicted observation, discriminating evidence, decision effect, and stop condition. Never present imaginative branching as evidence.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/counterfactual-fork

What's inside

Skill name
counterfactual-fork
Description
Generate bounded, decision-changing alternatives for plans, diagnoses, architectures, and strategic conclusions. Use when the result may depend on an uncertain premise, future condition, adversarial actor, timing, permission, scale, or causal interpretation. Produce at most three branches: baseline, strongest credible alternative, and failure/adversarial case. For each state the changed premise, predicted observation, discriminating evidence, decision effect, and stop condition. Never present imaginative branching as evidence.
License
MIT
Instructions
10 lines in SKILL.md · view on GitHub

Files (4)

  • SKILL.md
  • openai.yaml · agents/
  • icon.svg · assets/
  • branch-template.md · references/

SKILL.md (first lines)

# Counterfactual Fork

1. Freeze the current facts and decision.
2. Select one load-bearing premise per branch.
3. Build no more than three branches using [references/branch-template.md](references/branch-template.md).
4. Prefer alternatives that would reverse the decision or change mitigation.
5. Stop when additional branches do not alter action, risk, or verification.
6. Return the discriminating test before narrative elaboration.

From serhiipriadko2-sys/parallax, MIT.

More from serhiipriadko2-sys/parallax

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 28, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/serhiipriadko2-sys/parallax
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from serhiipriadko2-sys

Cite this page

counterfactual-fork skill. Agent Mart. https://agentmart.dev/skills/serhiipriadko2-sys-counterfactual-fork (last updated 2026-10-24)