agentsclimarketplace

He deepen plan

Skill jscraik/Agent-Skills/Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/team_automation/he-deepen-plan

Governed skill foundry and Skills SDK for Codex/AI coding agents: author, validate, evaluate, and sync runtime projections through ask.

Install
npx -y skills add jscraik/Agent-Skills --skill he-deepen-plan

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Deepen an existing implementation plan so sequencing, verification, and risk treatment are strong enough for execution. Use when the user wants Harness Engineering plan hardening before he-work.

SKILL.md

3.8 KB, 728 tokens by cl100k_base, as published. Nobody here has run it

Progressive Disclosure Entry

This entrypoint stays concise and keeps full operational context in archived references.

Use

  • Use this skill as normal for this Harness Engineering stage.
  • For full stage policy, workflow details, and examples, load the archived full guide.

Philosophy

  • Strengthen execution quality before coding begins.
  • Resolve sequencing and risk gaps while changes are still cheap.

When to use

  • Use when an existing plan needs sharper sequencing, testability, or risk treatment.
  • Use before he-work when plan readiness is uncertain.

Inputs

  • Existing plan artifact plus linked specs and constraints.
  • Dependencies, rollout constraints, and validation requirements.

Outputs

  • Deepened plan with explicit sequencing, checkpoints, and risk controls.
  • Clear readiness recommendation for he-work.
  • Include schema_version: 1 when structured output is requested.

Procedure

  1. Inspect current plan for ambiguity, hidden coupling, and missing checkpoints.
  2. Deepen task sequencing, validation strategy, and rollback posture.
  3. Return revised readiness and next action.

Validation

  • Ensure each task has observable completion criteria.
  • Ensure rollout, rollback, and dependency handling are explicit.
  • Fail fast: stop at first failed gate and do not proceed.

Constraints

  • Redact secrets, credentials, tokens, and sensitive data by default.
  • Do not introduce new scope without explicit justification.
  • Apply the context-disposition policy: move important still-valid context to references and index it when meaningful; intentionally discard stale, duplicated, unsafe, superseded, or low-signal text.

Anti-patterns

  • Increasing detail without improving executable clarity.
  • Deferring critical risk decisions to implementation time.

Full Context

Subagent Routing

Examples

  • "Can you deepen this implementation plan so every risky step has an owner, gate, and rollback?"
  • "Help me turn this thin plan into an execution sequence before I start editing code."
  • "This plan mentions validation, but it is vague. Tighten the order of tests, checks, and merge evidence."
  • "Can you inspect the risky steps in this plan and validate that each one has a concrete gate?"

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,970. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.