Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jscraik/Agent-Skillsnpx agentmods add skills/jscraik/agent-skills/plugin-factory-routerWrote 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/jscraik/agent-skills/plugin-factory-router)<a href="https://agentmods.dev/skills/jscraik/agent-skills/plugin-factory-router"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/plugin-factory-router/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/jscraik/agent-skills/plugin-factory-router"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/plugin-factory-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.01157 |
| Opus 5 | $0.00019 | $0.00579 |
| Sonnet 5 | $0.00008 | $0.00231 |
| Haiku 4.5 | $0.00004 | $0.00116 |
Grade A, and why
plugin-factory-router 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 8d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Factory Router
Use this entrypoint when a plugin request does not clearly name the right lane.
Philosophy
Route before acting. A plugin task should enter exactly one lane with clear trust, scope, and validation boundaries.
When to use
- Use when a plugin request is broad, mixed, or under-specified.
- Use when lane selection needs explicit routing before execution.
Required inputs
- User request text.
- Optional repository path, plugin source URL, or target plugin name.
- Any stated constraints (security posture, trust requirements, install target).
Deliverables
schema_version: "1"when structured output is requested.- One selected lane (
plugin-creator,plugin-installer,plugin-routerfollow-up, or plugin hardening through the factory router). - One-sentence rationale for the lane selection.
- One exact next command or prompt to execute.
- Plugin design checkpoint when authoring, rebuilding, auditing, or packaging: package boundary, public routing surface, child-skill separation, bundled hook surface, side-effect classes, progressive-disclosure references, install/projection determinism, and plugin-level eval coverage.
First-Principles Gate
Before plugin creation, hardening, refactor, or package-design handoff, identify
the user outcome, copied assumption, smallest effective mechanism, artifact
decision, and proof needed. Prefer IMPROVE_EXISTING, DOCS_ONLY, or
DO_NOT_BUILD when a new plugin, hook, MCP tool, app, or eval would only copy a
template or increase context load.
Failure mode
- If lane choice is materially ambiguous, ask one blocking clarification instead of guessing.
- If required context is missing (for example, unknown repository target), return blocked with the missing input.
Execution Boundaries
This router is read-only. It selects one plugin-factory lane and returns the next handoff. It must not install plugin code, execute plugin code, edit package files, refresh runtime mirrors, sync projections, or mutate external systems from the routing step.
What ships with it
6 files 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.
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.
- 8d ago First seen · 133 lines · 38 tokens per session scan A ba3ca4b85e3c
plugin-factory-router is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,157 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
ad-creative
Plan and produce advertising concepts, copy variants, visual directions, and test matrices for paid campaigns.
humanizer-zh
Revise Chinese text to sound specific, fluent, restrained, and human while preserving facts and author intent.
skill-creator
Design and write concise reusable KunAgent skills with valid triggers, real tools, and testable completion criteria.
daily-brief
Produce a dated, source-linked daily brief with prioritized developments, implications, and watch items.
imf-data
Retrieve and analyze IMF macroeconomic series, forecasts, and reserve-composition data.
scholar-research
Search, screen, synthesize, and cite scholarly literature and author metadata.