Agent skill

Verify Puppetmaster Jev

by professorpalmer in professorpalmer/Puppetmaster

Proves the Puppetmaster Jev transition behaves as specified: unset never uses the network, opt-in may skip the conflict auditor, and later versions only observe.

MITAuto-check passedTesting & QA

Install Verify Puppetmaster Jev

skills CLI
$ npx skills add professorpalmer/Puppetmaster --skill verify-puppetmaster-jev -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install professorpalmer/Puppetmaster verify-puppetmaster-jev --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/professorpalmer/Puppetmaster.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/verify-puppetmaster-jev .claude/skills/verify-puppetmaster-jev && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
verify-puppetmaster-jev
GitHub stars
467
Token cost
~525 tokens
SKILL.md length
189 words
Files
9 (incl. scripts)
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Proves the Puppetmaster Jev transition behaves as specified: unset never uses the network, opt-in may skip the conflict auditor, and later versions only observe.

  • Works in 5 steps: Helper JSON at… → v1_acts_on_opt_in=true (auditor skipped… → v234_match_today=true (launch / admit /… → …
  • Confirming the Jev transition still behaves correctly after a change in Puppetmaster
  • SKILL.md covers Launch, Doctor, Drive and Evidence, plus 2 more sections
  • Runs Python scripts from its folder; calls python

What it does

This is a verification routine for one feature of the Puppetmaster project, run in an isolated temporary store and never against your live `.puppetmaster/` state. It first runs `doctor.py`, which must report opted-in and acting both false in a clean environment, an importable `test_jev_transition` and no leaked `PUPPETMASTER_JEV` variables, and it stops if the check fails.

Proof comes from the `prove_observe.py` helper and the `tests.test_jev_transition` unit tests. A pass needs helper JSON written under `/tmp/verify-this/puppetmaster-jev/`, `v1_acts_on_opt_in=true`, `v234_match_today=true`, a zero unittest exit and a `## Jev` section in the stitcher preview only when a `jev_transition` gate exists. Live decisions are optional, only when you name a key source, and the key is loaded in process and never written to evidence. Cleanup kills only processes the run started.

When your agent uses it

  • Confirming the Jev transition still behaves correctly after a change in Puppetmaster
  • Checking that unset configuration makes no network calls
  • Collecting evidence that opt-in and ACT modes behave as designed

Example prompts

  • “Verify the Puppetmaster Jev transition and give me the evidence files.”
  • “Run the Jev doctor check and report whether the environment is clean.”
  • “Prove that versions 2 to 4 still only observe unless ACT is set.”

Requirements

  • Python 3
  • A Puppetmaster checkout that contains the Jev code

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Helper JSON at /tmp/verify-this/puppetmaster-jev/observe.json
  2. v1_acts_on_opt_in=true (auditor skipped without JEV_ACT)
  3. v234_match_today=true (launch / admit / enqueue unchanged)
  4. Unittest exit 0
  5. show / stitcher preview contains ## Jev only when a

What it can do on your machine

Read from SKILL.md and the folder at commit f4b23b3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Verify Puppetmaster Jev loads about 525 tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 189 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~525

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from professorpalmer/Puppetmaster at commit f4b23b3, republished under its MIT licence (© professorpalmer). 189 words, ~525 tokens.

Download SKILL.mdSave it as .claude/skills/verify-puppetmaster-jev/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
verify-puppetmaster-jev
description
Prove the Puppetmaster Jev transition oracle: unset never networks, opt-in may skip the conflict-auditor, V2–V4 stay observe unless ACT.
disable-model-invocation
true

Verify Puppetmaster Jev

Library plus CLI. Isolated temp store. Never use the user's live .puppetmaster/ state. Never print an OpenRouter key.

Launch

Ready: python -m unittest tests.test_jev_transition -q exits 0 from the Jev worktree (Puppetmaster-jev-oracle or the product checkout that contains puppetmaster/jev/).

bash
cd "$REPO"
.venv/bin/python -m unittest tests.test_jev_transition -q

Use the repo venv if present; otherwise python3 on PATH. Teardown is the process exit. Helpers write under /tmp/verify-this/puppetmaster-jev/ and must not delete prior receipts.

Doctor

bash
.cursor/skills/verify-puppetmaster-jev/scripts/doctor.py

Must report:

  • opted_in=false and acting=false in a cleared env
  • test_jev_transition importable
  • no PUPPETMASTER_JEV / PUPPETMASTER_JEV_ACT leak from the host after hermetic_env import

If doctor fails, fix the tree. Do not drive live Decisions.

Drive

Prefer the helper, then unittest, then an optional live observe.

bash
.cursor/skills/verify-puppetmaster-jev/scripts/prove_observe.py

Mapped features: features/README.md.

Evidence

A pass is:

  1. Helper JSON at /tmp/verify-this/puppetmaster-jev/observe.json
  2. v1_acts_on_opt_in=true (auditor skipped without JEV_ACT)
  3. v234_match_today=true (launch / admit / enqueue unchanged)
  4. Unittest exit 0
  5. show / stitcher preview contains ## Jev only when a jev_transition GATE exists

Live Decisions are optional and only when the user named a key source. Load the key in-process. Never write it to evidence.

Cleanup

Kill only the helper/unittest PIDs this run started. Leave /tmp/verify-this/puppetmaster-jev/ in place.

Helpers

  • .cursor/skills/verify-puppetmaster-jev/scripts/doctor.py
  • .cursor/skills/verify-puppetmaster-jev/scripts/prove_observe.py

© professorpalmer, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (scripts) in .cursor/skills/verify-puppetmaster-jev of professorpalmer/Puppetmaster.

  • SKILL.md
  • features/README.md
  • features/act.md
  • features/observe.md
  • features/unset.md
  • features/v1-on-opt-in.md
  • features/v2-on-job.md
  • scripts/doctor.py
  • scripts/prove_observe.py

Open the folder on GitHubat commit f4b23b3

Compare with similar skills

Verify Puppetmaster Jev next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Verify Puppetmaster Jev compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Verify Puppetmaster Jev this skillprofessorpalmer/Puppetmaster467—~525Automated safety check: PassMIT
Adk Verify Snippetsgoogle/adk-python22k—~1.4kAutomated safety check: PassApache-2.0
Hermetic Python Unit TestsdimensionalOS/dimos4.6k—~1.4kAutomated safety check: PassCustom licence
ONNX Runtime Test Runnermicrosoft/onnxruntime22k—~1.8kAutomated safety check: PassMIT
Simple Modern Uvjlevy/simple-modern-uv301—~1.9kAutomated safety check: PassMIT
Test Coverage Reviewareed1192/finance-news-aggregator149—~2.6kAutomated safety check: PassMIT

Similar skills

  • Adk Verify Snippets

    google/adk-python

    Official

    Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail…

    22k GitHub stars~1.4k tokensUpdated today
    Testing & QAAuto-check passed
  • Hermetic Python Unit Tests

    dimensionalOS/dimos

    Rules for writing, fixing and reviewing pytest unit tests that are hermetic: behavior-focused, deterministic, isolated and cheap to run.

    4.6k GitHub stars~1.4k tokensUpdated today
    Testing & QAAuto-check passed
  • ONNX Runtime Test Runner

    microsoft/onnxruntime

    Official

    Runs and debugs ONNX Runtime tests: Google Test executables for C++ and unittest or pytest for Python, with filters and build-directory guidance.

    22k GitHub stars~1.8k tokensUpdated today
    Testing & QAAuto-check passed
  • Simple Modern Uv

    jlevy/simple-modern-uv

    Start, selectively modernize, fully migrate, or update Python projects using simple-modern-uv practices: uv, ruff, BasedPyright, pytest, GitHub Actions CI, and tag-driven PyPI publishing.

    301 GitHub stars~1.9k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed
  • Test Coverage Review

    areed1192/finance-news-aggregator

    Audit, plan, write, and verify unit tests for Python projects using pytest.

    149 GitHub stars~2.6k tokensUpdated 5 mo ago
    Testing & QAAuto-check passed
  • Official

    Runs the ONNX Runtime transformers Python tests against a GPU wheel and proves the cuDNN flash attention path was used rather than a silent fallback.

    22k GitHub stars~2.9k tokensUpdated today
    Testing & QAAuto-check passed

More from professorpalmer/Puppetmaster

  • Puppetmaster Agent Orchestration

    professorpalmer/Puppetmaster

    Operates and supervises Puppetmaster, a multi-agent orchestrator, through its MCP tools or CLI, picking the right verb for edits, reviews, audits and long-running jobs.

    467 GitHub stars~3.2k tokensUpdated today
    Auto-check passed
  • Puppetmaster Pilot for Pi

    professorpalmer/Puppetmaster

    Pilot Puppetmaster from Pi. Pi is the TUI, not a leased worker. Use for start_implement, start_agentic, start_prewalk, effort-index, show, and nuking finished…

    467 GitHub stars~228 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Verify Puppetmaster Jev

What does Verify Puppetmaster Jev do?

Proves the Puppetmaster Jev transition behaves as specified: unset never uses the network, opt-in may skip the conflict auditor, and later versions only observe. puppetmaster/` state.py`, which must report opted-in and acting both false in a clean environment, an importable `test_jev_transition` and no leaked `PUPPETMASTER_JEV` variables, and it stops if the check fails.

When should I use Verify Puppetmaster Jev?

Verify Puppetmaster Jev fits situations like: confirming the Jev transition still behaves correctly after a change in Puppetmaster; checking that unset configuration makes no network calls; collecting evidence that opt-in and ACT modes behave as designed.

How do I install Verify Puppetmaster Jev in Claude Code?

Run `npx skills add professorpalmer/Puppetmaster --skill verify-puppetmaster-jev -a claude-code`. Or copy the skill folder (.cursor/skills/verify-puppetmaster-jev in professorpalmer/Puppetmaster) into .claude/skills/verify-puppetmaster-jev in your project. Claude Code loads it when a task matches its description.

How do I install Verify Puppetmaster Jev in Codex?

Run `npx skills add professorpalmer/Puppetmaster --skill verify-puppetmaster-jev -a codex`. Or copy the skill folder (.cursor/skills/verify-puppetmaster-jev in professorpalmer/Puppetmaster) into .agents/skills/verify-puppetmaster-jev in your project. Codex loads it when a task matches its description.

Can I use Verify Puppetmaster Jev in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add professorpalmer/Puppetmaster --skill verify-puppetmaster-jev -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verify-puppetmaster-jev, .gemini/skills/verify-puppetmaster-jev, .github/skills/verify-puppetmaster-jev and .opencode/skills/verify-puppetmaster-jev in your project.

What does Verify Puppetmaster Jev need to run?

Going by SKILL.md and its folder, Verify Puppetmaster Jev needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3; A Puppetmaster checkout that contains the Jev code.

Does Verify Puppetmaster Jev access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Verify Puppetmaster Jev safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Verify Puppetmaster Jev use?

Verify Puppetmaster Jev is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Verify Puppetmaster Jev use?

About 525 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Verify Puppetmaster Jev?

Skills that share tags, products or a category with Verify Puppetmaster Jev: Adk Verify Snippets (google/adk-python, 22k stars), Hermetic Python Unit Tests (dimensionalOS/dimos, 4.6k stars), ONNX Runtime Test Runner (microsoft/onnxruntime, 22k stars) and Simple Modern Uv (jlevy/simple-modern-uv, 301 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Verify Puppetmaster Jev?

professorpalmer (a GitHub user) maintains it in professorpalmer/Puppetmaster, which has 467 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 9, 2026.

Source: professorpalmer/Puppetmaster on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.