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/p47phoenix/claude-plugins/evaluativenpx skills add P47Phoenix/Claude-Plugins --skill evaluativegit clone --depth 1 https://github.com/P47Phoenix/Claude-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 | $0.00074 | $0.01292 |
| Opus 5 | $0.00037 | $0.00646 |
| Sonnet 5 | $0.00015 | $0.00258 |
| Haiku 4.5 | $0.00007 | $0.00129 |
Grade A, and why
research-types-evaluative 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 2d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluative Research Sub-Skill
Router-dispatched paradigm sub-skill for Evaluative research. Not directly model-invocable; the research-agent parent loads this sub-skill only when Phase 1 detection classifies the question as Evaluative.
When This Sub-Skill Loads
The parent router dispatches here when the input question contains signals like:
- "Did X work" / "Was X effective"
- "What was the impact of X"
- "Is X worth it"
- "Evaluate X" / "Assess X"
- Post-launch retrospectives, ROI assessments, "should we keep using X"
Disambiguation rule (from research-agent/references/research-type-patterns.md):
"What is the current adoption of X" (mapping a fact) → Descriptive. "Was X adoption successful" (judging merit) → Evaluative.
Framework Selection
| Framework | Use When |
|---|---|
| PICO | Default for Evaluative — intervention X is being judged against a comparison C on outcome O |
| PECO | Population was exposed to X (not actively choosing); evaluating the resulting effect |
| None | Single-option pre-post evaluation with no comparison group available |
PICO is the canonical Evaluative framework. SPICE applies only when the evaluation is qualitative/experiential rather than outcome-based.
Output Pattern: Impact Assessment
Use this pattern verbatim for the Findings section (parent skill's Phase 6 Synthesis output):
## Research Type: Evaluative
## Framework: PICO
P: [Population/context]
I: [Intervention/subject being evaluated]
C: [Comparison baseline]
O: [Outcomes measured]
## Inclusion/Exclusion Criteria
Include: [...]
Exclude: [...]
Date range: [from] to [to]
## Evidence Summary Table
| ID | Source | Design | Scope | Outcome Direction | GRADE |
|----|--------|--------|-------|-------------------|-------|
| S1 | ... | ... | ... | + / - / neutral | ⊕⊕⊕◯ |
## Outcome Synthesis
- Positive outcomes: [count / proportion of sources]
- Negative / neutral outcomes: [count / proportion]
- Heterogeneity: [Are results consistent or conflicting? Why?]
## Risk of Bias Summary
| Source | Selection | Performance | Detection | Attrition |
|--------|-----------|-------------|-----------|-----------|
| S1 | Low | ... | ... | ... |
## Verdict
[Conclusion with overall GRADE level and caveats]
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.
- 2d ago First seen · 113 lines · 74 tokens per session scan A 6905efd98c08
research-types-evaluative is a skill published in the GitHub repository P47Phoenix/Claude-Plugins (2 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 1,292 once invoked, about $0.0004 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.