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/brian-lai/para-programming-plugin/researchnpx skills add brian-lai/para-programming-plugin --skill researchgit clone --depth 1 https://github.com/brian-lai/para-programming-pluginWhat 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 | $0.00015 | $0.01041 |
| Opus 5 | $0.00008 | $0.00521 |
| Sonnet 5 | $0.00003 | $0.00208 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
research 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.
Perform deep codebase exploration and produce a context-compressed research document. This document becomes the primary input for /para:plan.
Usage
/para:research [task-description]
/para:research --scope=frontend # Focus research on a specific area
/para:research --specs # Emphasize API contract analysis
If no task description is provided, Claude will ask for one.
What It Does
-
Clarify focus — if the task description is broad or ambiguous, use AskUserQuestion to clarify scope, depth, and any specific concerns before proceeding. Skip if the task is narrow and well-defined.
-
Deep codebase exploration — perform thorough investigation across the relevant area:
- File structure and organization across the relevant area
- Key interfaces and contracts (OpenAPI specs, TypeScript interfaces, Protobuf, shared types)
- Test patterns, test coverage, and test framework conventions
- Dependency map for affected components (what depends on what)
- Error handling and graceful degradation patterns
- Logging and observability patterns
-
API contract analysis — if the project has OpenAPI/Swagger specs, interface files, or shared type definitions:
- Parse specs and cross-reference with actual implementation
- Flag any inconsistencies between spec and implementation
- Document the canonical source of truth for each contract
-
Pattern recognition — identify conventions, idioms, and anti-patterns that should inform planning:
- How errors are handled and propagated
- How dependencies are injected or wired
- How config is managed (env vars, config files, feature flags)
- Naming conventions, file organization patterns
-
Produce research document — write findings to
context/data/YYYY-MM-DD-task-name-research.mdusing the template fromresearch-template.md. The document should be:- High-signal, low-noise — include what matters for planning, not exhaustive file listings
- Structured for context compression — a planner reading only this document should have sufficient context to create a detailed plan
- Honest about gaps — explicitly call out what's undocumented, inconsistent, or surprising
What ships with it
1 file 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.
- 2d ago First seen · 113 lines · 15 tokens per session scan A d4059e946bf6
research is a skill published in the GitHub repository brian-lai/para-programming-plugin (7 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 1,041 once invoked, about $0.0001 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…