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/apurvbazari/claude-plugins/researchnpx skills add ApurvBazari/claude-plugins --skill researchgit clone --depth 1 https://github.com/ApurvBazari/claude-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/apurvbazari/claude-plugins/research)<a href="https://agentmods.dev/skills/apurvbazari/claude-plugins/research"><img src="https://agentmods.dev/badge/skills/apurvbazari/claude-plugins/research.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.03051 |
| Opus 5 | $0.00034 | $0.01525 |
| Sonnet 5 | $0.00014 | $0.00610 |
| Haiku 4.5 | $0.00007 | $0.00305 |
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 4d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Skill — the onboard v3 Research Engine
You are the onboard v3 research engine. You own orchestration and synthesis in your own context, you dispatch read-only specialist/verifier agents, and you are the sole writer of your outputs. You follow the lens engine pattern: fan out N schema-forced finders in ONE batch, run an adversarial verifier, synthesize, and write/return a schema-validated object.
This skill is user-invocable: false — it is invoked by another skill (/onboard:start Phase 2 (Research) after profile selection, and /onboard:adopt Step A2 at Full depth) or directly by a model. It is also directly model-invocable and testable standalone.
Overview
Input: projectPath + a depth preset (minimal | standard | comprehensive) + optional reconHints = { detectedRoots[], structureFacts }. When reconHints is absent (direct model-invocation), the engine self-detects source roots.
Output: the validated research-dossier object (per ../../schemas/research-dossier.json), returned to the caller AND written to .claude/onboard-research.json (+ four docs when the location dial says so).
Pipeline: roster discovery → in-skill scope/route → parallel specialist dispatch → Gate-1 collect/normalize/namespace → adversarial verify → synthesize + Gate-2 + wizardInferences → ask location + write → return.
Read these references as you run the matching step:
references/depth-profiles.md, references/specialist-roster.md, references/custom-specialist-contract.md, references/verification-procedure.md, references/synthesis-and-dossier.md, references/render-adapter.md (maps the dossier to a walkthrough session-model; the interactive HTML render now happens at the onboard pre-implementation gate — start Phase 5 (Plan → Preview → Gate)), references/dossier-merge.md (dimension-level merge of scoped re-research into a prior dossier — re-research only), references/wizard-inference-map.md.
Step 0: Empty-repo self-guard
What ships with it
8 files 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.
- references/custom-specialist-contract.md 7.6 KB
- references/depth-profiles.md 3.7 KB
- references/dossier-merge.md 3.1 KB
- references/render-adapter.md 4.1 KB
- references/specialist-roster.md 8.5 KB
- references/synthesis-and-dossier.md 8.2 KB
- references/verification-procedure.md 4.4 KB
- references/wizard-inference-map.md 4.6 KB
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.
- 4d ago First seen · 101 lines · 69 tokens per session scan A 51fb83a0f449
research is a skill published in the GitHub repository ApurvBazari/claude-plugins (0 stars, last pushed 28d ago), licensed MIT. It adds 69 tokens to every session and 3,051 once invoked, about $0.0003 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
cross-platform
Cross-platform development patterns for macOS, Windows, and Linux.
shell-scripting
Shell scripting best practices for cross-platform CLI tools.
c-notify
Send native macOS notification center alerts from the command line using terminal-notifier.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.