Name: harness-plan
Rating: 73.6 (1 reviews)
Author: Chachamaru127

harness-plan

HAR: Research-backed, team-validated task planning, Plans.md management, progress sync. Trigger: create a plan, add tasks, update Plans.md, mark complete, check progress. Do NOT load for: implementation, review, release.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is harness-plan in Chachamaru127/claude-code-harness

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, well-organized planning skill with concrete commands, clearly sequenced workflows and validation checkpoints, and clean one-level-deep references to real bundle files. The only weakness is conciseness — the body is long and some contract rules could be tightened or offloaded to references.

Suggestions

Tighten or move enumerated contract rules (e.g. the full pre-approval schema fields and lane/stage taxonomy) into a reference file to reduce inline token weight and lift conciseness.

Consolidate repeated Spec delta / Spec skip reason guidance, which appears in both the quality contract and the dual-source section, into a single authoritative statement.

Trim the session-launch guidance examples to one canonical block since the three priority cases overlap heavily.

Dimension	Reasoning	Score
Conciseness	Mostly lean domain-specific instruction rather than re-explained concepts, but the body is long and some enumerated contract rules and caveats could be tightened or pushed to references; it earns 2 rather than 3 because it is not fully tight.	2 / 3
Actionability	Provides concrete executable commands and exact artifacts — `/harness-plan create`, `scripts/plan-registry.sh switch roadmap`, `node scripts/generate-sprint-contract.js --plan roadmap 9.1.1`, marker tables, schema paths — copy-paste ready.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (create 11-step flow, quality flow, sync pipeline) with explicit validation checkpoints such as the spec.md/Plans.md dual-source check, pre-approval section, and lint-baseline setup task.	3 / 3
Progressive Disclosure	Body keeps a quick-reference overview inline and pushes detail to three real, one-level-deep referenced files (create.md, sync.md, planning-quality.md) that exist in the bundle, with clearly signaled navigation.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-structured description that states concrete capabilities, gives explicit natural-language triggers, and adds a negative scope for distinctiveness. Third-person voice is maintained throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "task planning, Plans.md management, progress sync" plus enumerated operations (create a plan, add tasks, update, mark complete, check progress), matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers both what (planning/management/sync) and when (explicit Trigger clause), and adds a negative scope; the 'Use when...' equivalent is present and explicit.	3 / 3
Trigger Term Quality	The explicit "Trigger: create a plan, add tasks, update Plans.md, mark complete, check progress" provides natural phrasings a user would actually say, giving good coverage of trigger terms.	3 / 3
Distinctiveness Conflict Risk	The "Do NOT load for: implementation, review, release" carve-out gives it a clear niche and distinguishes it from sibling harness skills, making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 5 missing, 5 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	14 / 16 Passed

Repository: Chachamaru127/claude-code-harness
Path: codex/.codex/skills/harness-plan/SKILL.md
Commit: 7a4e845

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.