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/understudy-ai/understudy/researchernpx skills add understudy-ai/understudy --skill researchergit clone --depth 1 https://github.com/understudy-ai/understudyWhat 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 | $0.00072 | $0.01020 |
| Opus 5 | $0.00036 | $0.00510 |
| Sonnet 5 | $0.00014 | $0.00204 |
| Haiku 4.5 | $0.00007 | $0.00102 |
Grade A, and why
researcher 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 3d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researcher
Use this skill for bounded, source-backed research.
Default goal: turn an open-ended question into a concise research output with explicit evidence, tradeoffs, and uncertainty.
When to use
Use this skill when the user wants any of:
- a comparison of products, vendors, tools, APIs, papers, or approaches
- a market or ecosystem landscape scan
- due diligence on a company, category, or technical option
- fact-checking or claim validation with citations
- a structured research brief, memo, or recommendation
Do not use this skill for:
- summarizing one URL, one article, one video, or one local file; use the more specific summarize flow instead
- GitHub issue, PR, release, or CI workflows; use the GitHub-specific skills instead
- purely internal codebase exploration with no web research component
Working style
Prefer current sources over memory. Use a small search budget first, then expand only if the evidence is weak or conflicting.
Unless the user already gave a narrow format, produce:
- Research goal
- Short answer or recommendation
- Comparison or findings
- Risks, caveats, and unknowns
- Sources
If the user asks for a persistent artifact, write a Markdown report under research/ with a short kebab-case filename that matches the topic.
Workflow
Follow these phases in order.
1. Frame the question
Before searching, extract or infer:
- the decision to be made
- the comparison axes or success criteria
- any hard constraints such as budget, platform, geography, or timeline
If one missing detail would materially change the answer, ask a short clarifying question. Otherwise proceed with a stated assumption.
2. Make a research plan
Break the work into 3-7 subquestions. Keep them concrete and decision-relevant.
Examples:
- What options belong in scope?
- What are the meaningful differences?
- What evidence is primary vs secondary?
- What risks or hidden costs matter?
3. Use a bounded search budget
Start with a tight first pass:
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.
- 3d ago First seen · 160 lines · 72 tokens per session scan A 91a2ec821a33
researcher is a skill published in the GitHub repository understudy-ai/understudy (456 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 1,020 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 2026-08-30.
Other skills, from other repositories
release-openclaw-maintainer
Prepare or verify OpenClaw stable, beta, and extended-stable releases, including backport discovery, changelogs, release notes, publish commands, and artifacts.
openclaw-testing
Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.
autoreview
Structured Codex, Claude, Amp, Pi, or Kimi code review when explicitly requested.
release-openclaw-ci
Run, watch, debug, and summarize OpenClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.
openclaw-ci-limits
Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe ramp-down/ramp-up changes. Use when tuning .github/workflows/, docs/ci.md, CI runner labels, matrix max-parallel…
auto-qa
Continuously audit, live-test, and stress-test the current OpenClaw codebase across at least ten independently scoped subsystem lanes; default to 100 independently verified, landed root-cause fixes, maintain an evidence-backed report, and announce each merged pull request immediately. Use for OpenClaw-wide autonomous…