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/comparativenpx skills add P47Phoenix/Claude-Plugins --skill comparativegit 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 | $0.00078 | $0.01372 |
| Opus 5 | $0.00039 | $0.00686 |
| Sonnet 5 | $0.00016 | $0.00274 |
| Haiku 4.5 | $0.00008 | $0.00137 |
Grade A, and why
research-types-comparative 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comparative Research Sub-Skill
Router-dispatched paradigm sub-skill for Comparative research. Not directly model-invocable; the research-agent parent loads this sub-skill only when Phase 1 detection classifies the question as Comparative.
When This Sub-Skill Loads
The parent router dispatches here when the input question contains signals like:
- "Compare X and Y"
- "Which is better"
- "Alternatives to X"
- "Options for X"
- "X vs. Y"
- "Trade-offs between"
- "Choose between"
Disambiguation rule (from research-agent/references/research-type-patterns.md):
"Compare X to understand Y" where understanding Y is the goal → Exploratory, not Comparative. Comparison is a method, not the purpose. Only route to Comparative when the user is choosing between identifiable options.
Framework Selection
| Framework | Use When |
|---|---|
| PICO | Comparing interventions on a measurable outcome (e.g., "Redis vs Memcached for session storage on latency") |
| None | Multi-criteria comparison with no single dominant outcome; use Decision Matrix with weighted criteria |
SPICE applies if the comparison is experiential ("from the perspective of senior engineers, async vs sync code review"). PECO is rare — exposure-comparison maps better to Evaluative.
Output Pattern: Decision Matrix
Use this pattern verbatim for the Findings section (parent skill's Phase 6 Synthesis output):
## Research Type: Comparative
## Framework: [None / PICO]
## Options Being Compared
[A], [B], [C]
## Evaluation Criteria (defined before gathering)
| Criterion | Weight | Rationale |
|-----------|--------|-----------|
| ... | x% | ... |
## Decision Matrix
| Criterion | Weight | Option A | Option B | Option C | Evidence [citations] |
|-----------|--------|----------|----------|----------|----------------------|
| ... | x% | [score] | [score] | [score] | [S1], [S2] |
## Dimension Deep-Dives
[For each high-weight criterion: detailed comparison with supporting evidence]
## SWOT per Option (when strategic context applies)
**Option A:** Strengths / Weaknesses / Opportunities / Threats
## Qualitative Comparative Analysis
Necessary conditions for success: [...]
Sufficient conditions for success: [...]
## Recommendation
**Recommended:** [Option X]
**Rationale:** [Why this best fits stated needs - with citations]
**Risk trade-offs:** [What is given up]
**Conditions where this changes:** [Edge cases that favor a different option]
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 · 115 lines · 78 tokens per session scan A 85a7005ca0db
research-types-comparative is a skill published in the GitHub repository P47Phoenix/Claude-Plugins (2 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 1,372 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…