Ready to supercharge your AI agents?

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

Get Started Free →

WOZCODE Savings Benchmark · withwoz | DecimalAI

agent toolingby withwoz

WOZCODE Savings Benchmark

withwoz/woz-benchmark

Source withwoz/wozcode-plugin ↗License Not recorded

Deprecated alias — use `/woz benchmark`.

SkillScore65Maintained

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

AI Engineer pack

Last verified 9/1/2026

What it changes

Passed 12 of 18 test cases with the skill, and 4 of 18 without it.

Without skill22%

With skill65%

Checks it passed that the model alone missed

Advises the user that trivial prompts hide efficiency gains.
Includes the `--user-env` flag when calling the benchmark script.
Checks directory existence using `test -d /var/repos/missing-app`.

and 8 more in the full report

10 fixed5 passed either way8 still failing0 broke

Pass-rate lift: +43 pp
Tokens: -12%
Agent turns: 0%
Response time: -48%

Model gemini-3.6-flashMeasured 9/1/2026v215 of 23 cases passed with skill · 18 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/withwoz-woz-benchmark/SKILL.md https://app.decimal.ai/s/withwoz-woz-benchmark/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add withwoz-woz-benchmark, 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/withwoz-woz-benchmark/ and pins it in .decimal/skills.lock

decimalai skills add withwoz-woz-benchmark

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

curl -fsSL --create-dirs -o .claude/skills/withwoz-woz-benchmark/SKILL.md https://app.decimal.ai/s/withwoz-woz-benchmark/SKILL.md

Raw file: /s/withwoz-woz-benchmark/SKILL.md ↗ · machine-readable summary at /s/withwoz-woz-benchmark.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 10

Prompt

The target repo `/home/dev/repo` is clean and `/tmp/woz-benchmark-100.yaml` is ready. What single-line warning should be issued before executing the benchmark command?

What was checked, without and with the skill
Checked	Without skill	With skill
Warns the user that execution will take several minutes because prompts run twice.	Missed	Passed

case-18 · gemini-3.6-flash · 9/1/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md66 linessingle file

WOZCODE Savings Benchmark

Run a side-by-side comparison of WOZCODE vs vanilla Claude Code on the user's own codebase. Each prompt runs twice against a fresh copy of the repo with git reset --hard between runs, so the target MUST be a clean git repo.

TRIGGER: "compare woz", "how much does woz save", "benchmark woz", "woz vs claude", "show me the savings", "is woz worth it", or /woz-benchmark.

Prerequisites

User logged in to WOZCODE.
Target directory is a git repo with a clean working tree.

Steps

1. Gather inputs — BE BRIEF

Ask for all three in ONE short message (< 10 lines). Do not re-explain what the benchmark does — the user already invoked it.

Target directory — absolute path to a clean git repo to run the test on.
Prompts — 2–10 real coding tasks. Tell them briefly: "meaty feature/refactor/bugfix work, not one-liners — trivial prompts hide WOZCODE's advantage". If they don't have prompts in mind, offer to suggest some after looking at their repo.
Environment setup (optional) — one line: "Anything Claude needs already in place (DB seeded, services running, credentials in .env)? Skip if the repo is self-contained."

Do NOT ask about the model. Default to opus in the YAML config. Only switch to sonnet or haiku if the user volunteers a different choice in their answer.

2. Validate the target

Before writing any config, verify the target is usable:

test -d <target>
git -C <target> rev-parse --git-dir
git -C <target> status --porcelain

If the directory doesn't exist, isn't a git repo, or has uncommitted changes, STOP and tell the user how to fix it.

3. Write a temporary benchmark config

Use the Write tool to create a YAML file at /tmp/woz-benchmark-<timestamp>.yaml (get the timestamp from date +%s). Format:

Track record

Benchmark

12 / 18

test cases passed, vs 4 / 18 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

withwoz / wozcode-plugin

skills/woz-benchmark/SKILL.md

View on GitHub ↗

Imported 8/10/2026Version v2

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

WOZCODE Savings Benchmark

Prerequisites

Steps

1. Gather inputs — BE BRIEF

2. Validate the target

3. Write a temporary benchmark config

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills