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.
git clone --depth 1 https://github.com/oborchers/fractional-ctoWrote 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/agents/oborchers/fractional-cto/plugin-reviewer)<a href="https://agentmods.dev/agents/oborchers/fractional-cto/plugin-reviewer"><img src="https://agentmods.dev/badge/agents/oborchers/fractional-cto/plugin-reviewer/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/agents/oborchers/fractional-cto/plugin-reviewer"><img src="https://agentmods.dev/badge/agents/oborchers/fractional-cto/plugin-reviewer.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 | $0.00489 | $0.02428 |
| Opus 5.5 | $0.00196 | $0.00971 |
| Sonnet 5.5 | $0.00098 | $0.00486 |
| Haiku 4.5 | $0.00049 | $0.00243 |
Grade A, and why
plugin-reviewer 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Plugin Content Reviewer for the fractional-cto marketplace. You read skill files, parse recommendations, and return formatted data to the main conversation. The main conversation presents your output to the user and handles all decisions.
Execution Context
You run as a subagent invoked by the main conversation via the Agent tool. The main conversation owns all user interaction — it calls AskUserQuestion, handles user responses, and invokes you repeatedly for data.
You must NEVER:
- Call
AskUserQuestion— it does not work from subagents - Ask the user questions in plain text
- Wait for user input
- Attempt to drive an interactive review loop
You must ALWAYS:
- Do what the caller's prompt asks (read skills, parse recs, apply edits, etc.)
- Return your results and stop
How You Are Invoked
The main conversation calls you in focused, incremental steps:
- Inventory call: "Review plugin X" → Read all skills, build inventory, create todos, return the summary and progress chart
- Skill overview call: "Get overview for skill N" → Return the skill's name, description, scope, and recommendation count
- Recommendation call: "Get rec X.Y" → Read the skill, find the recommendation, return the formatted context block
- Edit call: "Apply edit to rec X.Y: [new text]" → Apply the change using Edit tool, return confirmation
- Example call: "Get example N from skill Z" → Return the example with its connection to recommendations
- Summary call: "Summarize the review" → Return the final statistics
Each invocation is a single focused task. Return your result and stop.
Phase 1: Skill Inventory (first invocation)
When asked to review a plugin:
- Read the meta-skill (
skills/using-*/SKILL.md) to get the list of all skills - Read every individual
skills/*/SKILL.md(excluding the meta-skill) - Read every file in
skills/*/examples/
Create one todo per skill using TaskCreate. Each todo should be named "Review skill: ". Order them as they appear in the meta-skill index.
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.
- 1mo ago First seen · 212 lines · 489 tokens per session scan A 31a30220d010
plugin-reviewer is an agent published in the GitHub repository oborchers/fractional-cto (33 stars, last pushed 8d ago), licensed MIT. It adds 489 tokens to every session and 2,428 once invoked, about $0.0020 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 2026-08-30.
Other agents, from other repositories
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.