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.
npx skills add mdrideout/junjo --skill junjo-function-reviewgit clone --depth 1 https://github.com/mdrideout/junjoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mdrideout/junjo/junjo-function-review)<a href="https://agentmods.dev/skills/mdrideout/junjo/junjo-function-review"><img src="https://agentmods.dev/badge/skills/mdrideout/junjo/junjo-function-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mdrideout/junjo/junjo-function-review"><img src="https://agentmods.dev/badge/skills/mdrideout/junjo/junjo-function-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.00387 |
| Opus 5.5 | $0.00016 | $0.00155 |
| Sonnet 5.5 | $0.00008 | $0.00077 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
junjo-function-review 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 25d 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.
What it actually says
Junjo FunctionReview
Use the installed Junjo MCP tools. The local bridge must already be running. If the tools are unavailable, report that; do not substitute shell execution or call a model API.
The coordinator starts an execution with start_execution. Set capture=true
when the user requests diagnostic capture; otherwise leave it false. Host
telemetry export must also be configured for model spans to appear.
For the concurrent proof, spawn two native Codex subagents. Give each the
execution ID and one fixture (buggy or correct). Each subagent:
- Calls
start_review(execution_id, fixture)once. - Reads the returned instructions, input, and output schema.
- Uses its own reasoning to produce the result, then calls
complete_step(request_id, result). - Prints the complete tool response unchanged. Its receipt lets the bridge correlate the actual Codex request without guessing from timestamps.
- If the response has
status=work, reasons about that next step in a new model response and repeats. Never precompute both steps in one tool script. - Returns the final workflow result to the coordinator.
The coordinator waits for both subagents and calls finish_execution.
For a single-worker proof, perform the same worker loop in one subagent.
Use finish_execution(cancel=true) when the user cancels this execution.
Do not edit the snippets: the example asks for review evidence only.
execution_status reports submitted steps and observed model-span counts.
Host export is asynchronous, so workflow completion can precede model evidence.
Report zero model spans as missing evidence, not successful model tracing.
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.
- 25d ago First seen · 37 lines · 39 tokens per session scan A 9a248241ff27
junjo-function-review is a skill published in the GitHub repository mdrideout/junjo (20 stars, last pushed 8d ago), licensed Apache-2.0. It adds 39 tokens to every session and 387 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-21.
Other skills, from other repositories
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
implement-universal
Harness-agnostic version of /implement. Drives a single workshop ticket through the SWE→Tester loop in ONE conversation, with the role prompts bundled as agents/software-engineer.md and agents/tester.md instead of being launched as subagents. Resolves the ticket from implementyourself/tasks/, creates an…
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
resolve-repro-audit
Audit a recovered repro patch, assertions, and behavioral baseline before authoring or reviewing.