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/block/buzz/github-researchnpx skills add block/buzz --skill github-researchgit clone --depth 1 https://github.com/block/buzzWhat 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 | $0.00019 | $0.00382 |
| Opus 5 | $0.00010 | $0.00191 |
| Sonnet 5 | $0.00004 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
github-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 yesterday.
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.
What it actually says
GitHub Research
Search GitHub for prior art, implementation patterns, and maintainer decisions.
Commands
# Search issues
gh search issues "topic" --repo owner/repo --limit 20 \
--json number,title,state,url
# Search merged PRs (highest signal)
gh search prs "topic" --repo owner/repo --merged --limit 20 \
--json number,title,url
# Search code (use query syntax for path filtering)
gh search code "pattern path:src/" --repo owner/repo --limit 20 \
--json path,textMatches
# Get full issue or PR details
gh issue view 123 --repo owner/repo --json number,title,body,comments
gh pr view 456 --repo owner/repo --json number,title,body,reviews,files
Rate Limits
- Search API: 30 requests/minute
- Check with:
gh api rate_limit --jq '.resources.search'
Signal Ranking
- Merged PRs — decisions that shipped
- Maintainer comments — authoritative
- Closed issues with solutions — problems solved
- Open issues — current problems (lower signal)
Report Format
## Research: [Topic]
### Summary
- Key finding 1 [#123]
- Key finding 2 [PR #456]
### Findings
1. **#123: [Title]** — [summary]. URL: https://...
2. **PR #456: [Title]** — [what it changed]. URL: https://...
### Gaps
- [What you looked for but didn't find]
Always include URLs. If nothing relevant exists, say so.
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.
- yesterday First seen · 60 lines · 19 tokens per session scan A c9b68613be2b
github-research is a skill published in the GitHub repository block/buzz (31,513 stars, last pushed 2d ago), licensed Apache-2.0. It adds 19 tokens to every session and 382 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…