junjo-evaluation

A workflow for evaluating the quality of an application or AI agent using Junjo Studio. It turns a quality goal into test cases, runs them, and collects exact run evidence for a report.

In plain words
What is it for?
Use it to measure current behavior, create or resume evaluations of Node, workflow, or agent targets, inspect traces, and assess an improvement after code or prompt changes are authorized.
Why use it?
It removes the manual work of preparing evaluation data, choosing commands, tracking run IDs, checking results, and comparing outcomes.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/mdrideout/junjo/junjo-evaluation
Any agent
npx skills add mdrideout/junjo --skill junjo-evaluation
Clone the repo
git clone --depth 1 https://github.com/mdrideout/junjo

Made for: Claude Code, Codex.

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,877 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00083 $0.01877
Opus 5 $0.00042 $0.00938
Sonnet 5 $0.00017 $0.00375
Haiku 4.5 $0.00008 $0.00188

Measured 3d ago against content hash d54cee925029, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

junjo-evaluation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

sdks/python/skills/junjo-evaluation/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Junjo Evaluation

Operate Junjo Evaluation from the application repository using the installed junjo SDK and CLI. Do not require access to the Junjo source repository.

Operating contract

Treat a product-quality objective such as “evaluate local-place realism” as sufficient direction to operate the complete baseline workflow. Own target and evaluator discovery, scenario design, temporary JSON artifacts, Studio dataset operations, run execution, identifier tracking, evidence retrieval, analysis, and the final report.

Do not ask the developer to write JSON, choose CLI flags, copy identifiers, poll evidence, or run commands. Ask only when product intent is materially ambiguous or a real prerequisite or authorization is missing.

For a baseline request, measure current committed behavior and do not modify application behavior. Modify prompts or code, run tests, or create commits only when the developer authorizes an improvement iteration. Never commit unrelated work.

Boundaries

  • Use the installed junjo eval CLI as the exact command and schema source of truth. Inspect its current --help; do not reproduce its mechanics with ad hoc HTTP or shell clients.
  • Use junjo.evaluation and junjo.studio when application code or direct Python integration is required. Do not copy Studio clients, DTOs, runners, or generic evaluation mechanics into the application.
  • Keep JUNJO_AI_STUDIO_CLI_TOKEN separate from JUNJO_AI_STUDIO_API_KEY. Never print, persist, or pass either secret as a routine command argument.
  • Preserve the application's real OpenTelemetry service identity. Evaluation classification augments ordinary application telemetry; it does not create a fake evaluation service.
  • Use bounded SDK/CLI evidence and comparison queries rather than Studio's raw observability routes.
  • Let Junjo execute Attempts sequentially. Do not add application-local concurrency around the runner.

1. Inspect the application

Read the application repository's instructions and locate its configured environment without exposing secrets. Inspect the nearest code, prompts, fixtures, tests, and domain rules relevant to the requested quality objective.

Read the full file on GitHub · 201 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 201 lines · 83 tokens per session scan A d54cee925029

Subscribe to this mod's changes

junjo-evaluation is a skill published in the GitHub repository mdrideout/junjo (20 stars, last pushed 3d ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,877 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

agent-self-scheduling

Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.

sickn33/agentic-awesome-skills · 24 tokens

dagr-producer

Emit and maintain a dagr run file — a live, contract-valid JSON description of recursive projects, tasks, attempts, gates, evidence, policies, events, and operator-message resolutions that dagr view renders as a DAG. Use when orchestrating agents or tracking multi-step work that a dagr pane should display.

aemrebarut/herdr-dagr · 70 tokens

diataxis-docs-writer

Write or improve software documentation using the Diátaxis framework — four documentation types (tutorials, how-to guides, reference, explanation), each serving a different user need. Use it whenever you're about to write or revise documentation for a finished feature, implementation, API, library, CLI, service, or…

calf-ai/calfkit-sdk · 218 tokens

opensource-guide-coach

Use when a user wants guidance on starting, contributing to, growing, governing, funding, securing, or sustaining an open source project, or asks about contributor onboarding, community health, maintainer burnout, code of conduct, metrics, legal basics, or open source project adoption.

calf-ai/calfkit-sdk · 60 tokens

pytest-coverage

Run pytest tests with coverage, discover lines missing coverage, and increase coverage to 100%.

calf-ai/calfkit-sdk · 22 tokens

writing-workspace-jobs

Author FSM workspace jobs. Use when creating, editing, or debugging jobs, signals, or FSM workflows in workspace.yml.

friday-platform/friday-studio · 30 tokens