Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Plan — measured AI agent skill | DecimalAI

hmbown/plan

NewSkillScoreMaintained

Turn a sufficiently understood task into an ordered implementation plan with dependencies and verification. Orchestrate CodeWhale’s native plan state; do not build a parallel planner.

by hmbown

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Project Management pack

decimalai skills pull hmbown-plan

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/hmbown-plan/SKILL.md

Raw file: /s/hmbown-plan/SKILL.md ↗ · machine-readable summary at /s/hmbown-plan.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 22h ago

—-29% tokens0% turns55% of whole cases pass with skill (12/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-09	✗→✓	▲ Improved	1%	0%
case-02	✗→✓	▲ Improved	-56%	0%
case-10	✗→✓	▲ Improved	13%	0%
case-04	✗→✓	▲ Improved	-38%	0%
case-20	✓→✗	▼ Worse	-40%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

hmbown / codewhale

crates/tui/assets/skills/plan/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Plan

When to use

Use when the task is understood well enough to sequence work, but not yet a single obvious next edit.

Non-goals

Do not plan while key goals are still unknown — use interview first.
Do not create a second planner outside CodeWhale plan/Work state.

Workflow

Restate the goal and constraints.
List ordered steps with dependencies.
Mark verification for each risky step.
Write the plan into CodeWhale’s native plan/Work surface.
Wait for authorization before broad implementation.

Output shape

Goal
Steps (ordered)
Verification
Risks / open questions

Want to see if hmbown/plan would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.