Ready to supercharge your AI agents?

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

Get Started Free →

Create A Small Plan · optim-agent | DecimalAI

agent toolingby optim-agent

Create A Small Plan

optim-agent/create-a-small-plan

Source optim-agent/optim-plans ↗License MIT

Create a small Prime Agent plan before implementation.

SkillScore50Maintained

Automatic

Coding pack

Last verified 9/3/2026

What it changes

Passed 8 of 16 test cases with the skill, and 4 of 16 without it.

Without skill27%

With skill50%

Checks it passed that the model alone missed

Asks planning questions one at a time
Places Auto-complete as the last option
Names the revised plan document PLAN_v2.md

and 6 more in the full report

7 fixed4 passed either way9 still failing2 broke

Pass-rate lift: +23 pp
Tokens: -44%
Agent turns: 0%
Response time: -41%

Model gemini-3.6-flashMeasured 9/3/2026v111 of 22 cases passed with skill · 16 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/optim-agent-create-a-small-plan/SKILL.md https://app.decimal.ai/s/optim-agent-create-a-small-plan/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add optim-agent-create-a-small-plan, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/optim-agent-create-a-small-plan/ and pins it in .decimal/skills.lock

decimalai skills add optim-agent-create-a-small-plan

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/optim-agent-create-a-small-plan/SKILL.md https://app.decimal.ai/s/optim-agent-create-a-small-plan/SKILL.md

Raw file: /s/optim-agent-create-a-small-plan/SKILL.md ↗ · machine-readable summary at /s/optim-agent-create-a-small-plan.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

Following the single critique pass on our small error-handling update, we updated the plan artifact to address the feedback. What file name should be used for this updated plan?

What was checked, without and with the skill
Checked	Without skill	With skill
Names the revised plan document PLAN_v2.md	Missed	Passed

case-13 · gemini-3.6-flash · 9/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md25 linessingle file

Create A Small Plan

Use this skill when the user wants a compact plan before a repository change.

Setup

Read ../_shared/references/prime-planning-workflow.md, ../_shared/references/state-and-config.md, and ../_shared/references/plan-artifact-template.md.
Initialize state with python3 scripts/optim_plans.py init --repo <target-repo> --topic <topic> --plan-level create-a-small-plan --request-text <original-request>.
Use .git/optim-plans for controller state and docs/optim-plans/YYYY-MM-DD-topic/ for public artifacts.

Depth Contract

Inspect the target Git repo read-only before the first product question.
Ask 1 to 3 planning questions, one at a time.
Use the standard choice prompt format: recommended first, Other second-last, Auto-complete last.
Ask the mandatory final scope confirmation before writing PLAN_v1.md.
Write PLAN_v1.md under docs/optim-plans/YYYY-MM-DD-topic/.
Run exactly one reviewer or criticizer refinement round unless the user explicitly accepts the plan for native execution.
After that one refinement round, revise to PLAN_v2.md if needed, then ask the native execution handoff question without Auto-complete.

Fit

Choose this level for a change limited to a few local files, clear ownership, low architectural risk, and focused verification.

Escalate to create-a-plan when the plan needs external API semantics, dependency behavior, compatibility research, cross-module design, or more than three meaningful decisions.

Track record

Benchmark

8 / 16

test cases passed, vs 4 / 16 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

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

optim-agent / optim-plans

skills/create-a-small-plan/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Create A Small Plan

Setup

Depth Contract

Fit

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills