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 stellarshenson/claude-code-plugins --skill evaluategit clone --depth 1 https://github.com/stellarshenson/claude-code-pluginsWrote 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/stellarshenson/claude-code-plugins/evaluate)<a href="https://agentmods.dev/skills/stellarshenson/claude-code-plugins/evaluate"><img src="https://agentmods.dev/badge/skills/stellarshenson/claude-code-plugins/evaluate/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/stellarshenson/claude-code-plugins/evaluate"><img src="https://agentmods.dev/badge/skills/stellarshenson/claude-code-plugins/evaluate.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 | $0.00040 | $0.01436 |
| Opus 5.5 | $0.00016 | $0.00574 |
| Sonnet 5.5 | $0.00008 | $0.00287 |
| Haiku 4.5 | $0.00004 | $0.00144 |
Grade A, and why
evaluate 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devil's Advocate - Evaluate (Baseline)
Generate concern catalogue and scorecard. Run after setup.
Task Tracking
MANDATORY: Use TaskCreate/TaskUpdate per step (read context, generate catalogue, score, create v01). Mark in_progress/completed.
Prerequisites: devils_advocate.md and fact_repository.md must exist. Otherwise: tell user to run /devils-advocate:setup.
Step 1: Read context
Read target document, devils_advocate.md, fact_repository.md in full.
Step 2: Generate concern catalogue
Fibonacci scale (1, 2, 3, 5, 8):
- Likelihood (1-8): chance persona raises it
- Impact (1-8): damage if unaddressed
- Risk = Likelihood x Impact (1-64)
Risk adjustment: review full set. Adjust where interactions amplify. Document: Risk: N (adjusted from L x I = M, reason: ...).
Concern template:
### N. "[Concern as the devil would phrase it]"
**Likelihood: N** | **Impact: N** | **Risk: N**
**Their take**: what devil thinks. Write as them.
**Reality**: factual counter. Reference fact_repository.md.
**Response**: how to address it.
Categories (persona-weighted):
- Accuracy gaps, trust signals, cognitive load, omissions
- Forward-looking, legal/contractual, professional responsibility
No negative risk scores. Strengths go in "Reality" and "Response".
Step 3: Scorecard
Score 0-100% per concern.
| Score | Devil's reaction |
|---|---|
| 95-100% | "I have no issue" |
| 80-94% | "Fine, but I noticed..." |
| 60-79% | "Doesn't fully answer" |
| 40-59% | "This is a problem" |
| 20-39% | "You're hiding something" |
| 0-19% | "Makes it worse" |
Scorecard format (append to devils_advocate.md):
## Scorecard v01 ([document name] as-is)
| # | Concern | Risk | Score | Residual | Reasoning |
|---|---------|------|-------|----------|-----------|
| 1 | [name] | 25 | 85% | 3.75 | [specific text reference + quality assessment] |
- Residual =
risk x (1 - score) - Document score = sum of residuals (minimise)
- Reasoning MUST quote specific text
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 Changed acbd464a4dd3
- 1mo ago First seen · 162 lines · 40 tokens per session scan A 47e3223d0496
evaluate is a skill published in the GitHub repository stellarshenson/claude-code-plugins (4 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,436 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…