# Helix

> Use when uncertain or inherited work risks unframed experiments or accumulating plans and needs one bounded evidence loop plus a compact checkpoint; not for routine work with clear scope and order.

- Skill: `thekashey/helix` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add thekashey/helix`
- Raw SKILL.md: https://api.skillmd.com/api/skills/thekashey/helix/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: theKashey (https://skillmd.com/u/thekashey)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/thekashey/helix

---


# Helix

Advance uncertain work by closing one evidence loop at a time. Cadence is a
completed **Arrange → Act → Assert/Collapse** transition; activity volume is not
progress.

## Keep the transition laws visible

- **Checkpoint before work.** Require an explicitly configured surface,
  reference, representation, and read/write authority. If any is missing,
  return `NEEDS-HUMAN-DECISION`; never invent a file, service, or transcript
  fallback. A Ralph-style or goal loop's persisted prompt or plan file carries
  execution and intent, not learning; treat it as the checkpoint only when the
  user has configured it as the surface.
- **Arrange before Act.** Freeze the supplied situation or need, intended
  effect and proof, authority and boundary, selected branch's contribution, one
  move's maximum scope, observation source, review point, and expected plus
  disconfirming readbacks. Missing framing makes **Next** a repair or block,
  never permission to experiment.
  Helix sequences a supplied move; it does not classify the causal regime or
  design the probe. When installed, Read the Terrain owns that upstream work.
- **Act once.** Keep one move in flight. Give its executor only the outcome
  boundary, branch contribution, move, observation source, review point, and
  readbacks. Stop at the first readback, review point, or boundary.
- **Assert before another Act.** Append the immutable observation beside the
  frozen readbacks, then classify it as `Expected`, `Disconfirming`, `Mixed`, or
  `Inconclusive`. Effort, confidence, and retrospective producer narration are
  not evidence.
- **Collapse every ended move.** Sort delivered work to its store of record,
  retired work to an epitaph, and everything else to deliberate disposal.
  Rewrite the checkpoint with exactly one **Next** before another Act.

The checkpoint stores verdicts, not deliberation: outcome, surviving branches,
active arranged moves and results, open links, epitaphs, and one **Next**. Re-derive
candidates and ranking each cycle. A matching readback establishes only what
was observed inside its boundary; it does not prove value, correctness, or
causality.

## Run the current state

Start at the first incomplete transition; never repeat a completed phase.

1. Read the checkpoint whole.
2. **Expand:** derive branches from the outcome and latest results; drop any
   candidate whose possible results leave the next decision unchanged. Check
   epitaph resurrection conditions, select one branch, and keep implementation
   inspection behind the arranged move.
3. **Spike:** Arrange, then Act once.
4. **Collapse:** Assert, sort the ended move, rewrite the checkpoint, and select
   one **Next**.

Load only the applicable section of
[checkpoint and edge cases](references/checkpoint-and-edge-cases.md):

- configure or reconstruct a checkpoint;
- repair an orphan or unknown link;
- resolve `Mixed` or `Inconclusive` evidence;
- retire, resurrect, retry, or dispose of work.

Return the checkpoint reference, **Next**, and every orphan, unknown, or
authority block.