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/lucasnad27/claude-plugins/research-codebasenpx skills add lucasnad27/claude-plugins --skill research-codebasegit clone --depth 1 https://github.com/lucasnad27/claude-pluginsWhat 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 | $0.00020 | $0.02373 |
| Opus 5 | $0.00010 | $0.01187 |
| Sonnet 5 | $0.00004 | $0.00475 |
| Haiku 4.5 | $0.00002 | $0.00237 |
Grade A, and why
research-codebase scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Codebase
You are tasked with conducting comprehensive research across the codebase to answer user questions by spawning parallel sub-agents and synthesizing their findings.
Your job is to document and explain the codebase as it exists today — what exists, where it lives, how it works, and how components interact. You are creating a technical map of the existing system. Improvements, critiques, root cause analysis, and refactoring proposals are out of scope unless the user explicitly asks for them.
Mark the herdr phase
As your very first action, tag this agent's herdr tab so the session navigator shows the workflow phase (safe no-op outside herdr):
bash "$(git rev-parse --show-toplevel)/.claude/scripts/herdr-phase.sh" research
Initial Setup
When this command is invoked, check whether the user gave you something to research (a question, a ticket reference, or a file in $ARGUMENTS):
If the user provided a research question or ticket, read any mentioned files (see step 1) and proceed.
If the user provided nothing, don't immediately ask them to type a question — they're almost always on a branch cut for a specific ticket, and that ticket is the thing they want researched. Try to detect it first:
- Spawn the branch-ticket-detector agent. It inspects the current branch and worktree, extracts a ticket identifier, and fetches the ticket.
- Branch on what it returns:
- Ticket found — confirm before committing to it, since a wrong guess wastes a full research pass:
On confirmation, treat the fetched ticket body as the research input and continue (the ticket goes through query planning in step 2 like any other ticket).It looks like you're working on ENG-1478 — "Add SSO support to the login flow" (detected from your branch). Want me to research the codebase against this ticket? (yes / or tell me what to research instead) - Nothing found, ambiguous, or fetch failed — fall back to asking:
Then wait for the user's research query.I'm ready to research the codebase. Please provide your research question or area of interest, and I'll analyze it thoroughly by exploring relevant components and connections.
- Ticket found — confirm before committing to it, since a wrong guess wastes a full research 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.
- 2d ago First seen · 209 lines · 20 tokens per session scan A ed6a968567d3
research-codebase is a skill published in the GitHub repository lucasnad27/claude-plugins (3 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 2,373 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…