Borrowing it
Nothing to install: this file belongs to friedbotstudio/baseline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/friedbotstudio/baseline/main/.claude/skills/research/SKILL.mdgit clone --depth 1 https://github.com/friedbotstudio/baselineWrote 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/friedbotstudio/baseline/research)<a href="https://agentmods.dev/skills/friedbotstudio/baseline/research"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/research/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/friedbotstudio/baseline/research"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00096 | $0.01542 |
| Opus 5.5 | $0.00038 | $0.00617 |
| Sonnet 5.5 | $0.00019 | $0.00308 |
| Haiku 4.5 | $0.00010 | $0.00154 |
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 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are surfacing a small set of candidate approaches to a task, with honest tradeoffs, so the spec author can pick one. Decisions are not made here — the human reviewer decides at /spec. Your job is to lay out the option space.
Prereqs
scoutincompletedOR inexceptions.
Inputs
- The intake at
docs/intake/<slug>.md— Constraints and Acceptance criteria sections filter which approaches are viable. - The scout report at
docs/scout/<slug>.md— patterns in use, touchpoints, landmines. - The BRD at
docs/brd/<slug>.mdif present — NFR-### requirements (latency, compliance, etc.). - The existing tech stack — read
package.json,pyproject.toml,go.mod, lockfiles.
Mandatory: verify library APIs against current docs (the provider is a default)
For any library you intend to cite, verify its API against current documentation — never training recall.
The MCP server that fetches those docs is named in .claude/docs-provider.json; resolve it with readDocsProvider from .claude/skills/lib/docs-provider.mjs, which falls back to the shipped default when the pointer is absent or unreadable. Use that server's own library-resolution and documentation-fetch tools — read their names from the tool list rather than assuming a shape, because a project may point at a different provider.
Never cite an API from memory. Record the version present in the lockfile and confirm the docs match that major version. If the provider has no coverage (or the project ships none), fall back to WebFetch against the library's official docs / llms.txt and note the source. Any current-docs source satisfies the rule — the declared provider is the convenient default, not a hard requirement (seed.md §2.5).
Method
-
Retrieve prior art before deriving. Run:
node .claude/skills/research/retrieve.mjs --slug <slug> --terms "<intake topics + scout touched modules>" \ --touched '["<scout-touched path>","<scout-touched path>"]' --spec-dir docs/system 2>/dev/null
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.
- 1mo ago First seen · 97 lines · 96 tokens per session scan A 0e7fbd966823
research is a skill published in the GitHub repository friedbotstudio/baseline (14 stars, last pushed 13d ago), licensed Apache-2.0. It adds 96 tokens to every session and 1,542 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
code-review-with-lsp
Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.
i18n-check
An internationalization (i18n) check for software that supports multiple languages. It compares translation files with the text and translation keys used by the code.
vue-best-practices
A review checklist for Vue 2 and Vue 3 components, covering component names, prop declarations, TypeScript casts, API styles and complex template expressions.
gdpr-audit
GDPR compliance audit of code, plans, schemas, or IaC. Produces a findings report with article citations, severity, confidence, and fixes; flags evidence gaps. Not a substitute for a DPO/lawyer.
cognitive-walkthrough
Deep-dive usability evaluation of specific user tasks. Simulates novice user cognition step-by-step to identify learnability issues, unclear actions, and points of confusion.
owasp-ai-testing
AI trustworthiness testing using OWASP AI Testing Guide v1. Execute 32 test cases across 4 layers (Application, Model, Infrastructure, Data) with practical payloads and remediation.