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 agentmods add skills/stellarshenson/claude-code-plugins/setupnpx skills add stellarshenson/claude-code-plugins --skill setupgit clone --depth 1 https://github.com/stellarshenson/claude-code-pluginsWhat 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 | $0.00044 | $0.00742 |
| Opus 5 | $0.00022 | $0.00371 |
| Sonnet 5 | $0.00009 | $0.00148 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
setup 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 yesterday.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devil's Advocate - Setup
Build persona and fact repository. Always first step.
Task Tracking
MANDATORY: Use TaskCreate/TaskUpdate for identifying target, building persona, harvesting facts. Mark in_progress/completed.
Artefacts produced
devils_advocate.md- persona definitionfact_repository.md- verified claims
Place alongside target document.
Step 1: Identify target document
Ask user which document. Read in full.
Step 2: Build Devil Persona
MANDATORY: Persona BEFORE concerns.
Source A: User-provided seed
Seed document (evaluation, review) alongside target. Infer persona from tone, priorities. Confirm with user.
Source B: User describes persona
Ask ALL in ONE message:
"Describe the toughest reader for this document:
- Who are they? (role, seniority)
- What do they care about most? (cost, risk, timeline, compliance, quality)
- Style? (data-driven, gut-feel, political, legalistic)
- Default bias? (skeptical, risk-averse, cost-focused)
- What triggers them? (blame-shifting, excuses, missing numbers)
- What can they do? (approve, reject, escalate)"
Source C: No seed or persona
MUST ask. Never proceed with generic concerns. One message:
"No persona provided. Either: (a) Describe toughest reader (role, priorities, biases), OR (b) List 2-4 roles and I'll build a composite devil"
For groups: merge priorities (union), harshest bias per persona, weight likelihood by which persona raises each concern.
Persona documentation
Write to devils_advocate.md:
# Devil's Advocate - [Project Name]
## The Devil
**Role**: [title and context]
**Cares about**: [2-3 priorities in order]
**Style**: [how they process information]
**Default bias**: [their starting stance]
**Triggers**: [what makes them react negatively]
**Decision**: [what they can do with the document]
**Source**: [seed-inferred / user-described / composite]
---
Step 3: Harvest facts into fact_repository.md
Scan sources. Extract verifiable claims with sources.
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.
- yesterday First seen · 114 lines · 44 tokens per session scan A 6da654a0556c
setup is a skill published in the GitHub repository stellarshenson/claude-code-plugins (3 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 742 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…