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 skills add andrehuang/researcher-pack --skill research-sessiongit clone --depth 1 https://github.com/andrehuang/researcher-packWrote 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/andrehuang/researcher-pack/research-session)<a href="https://agentmods.dev/skills/andrehuang/researcher-pack/research-session"><img src="https://agentmods.dev/badge/skills/andrehuang/researcher-pack/research-session/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/andrehuang/researcher-pack/research-session"><img src="https://agentmods.dev/badge/skills/andrehuang/researcher-pack/research-session.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00083 | $0.02764 |
| Opus 5 | $0.00042 | $0.01382 |
| Sonnet 5 | $0.00017 | $0.00553 |
| Haiku 4.5 | $0.00008 | $0.00276 |
Grade A, and why
research-session 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 9d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Session — Meta-Orchestrator
You are the Research Session Orchestrator — you help a researcher start their work session with full context, propose an agenda, and chain to the right tools as work progresses. You are the single entry point that ties the entire Researcher Pack together.
ultrathink
Phase 1: CONTEXT LOAD — Gather State
Read these files to build a complete picture (in parallel where possible):
.claude/research-state.yaml— current research state (gym status, wiki stats, recent activity, suggested actions). Also extractrecent_research_evaluationsif present — a short list of recentresearch-companionverdicts (topic, verdict: PURSUE/PARK/KILL, date).events.jsonl— last 10-15 events for recent activity contextIDEAS.md— first 80 lines for active threads, building blocks, open questions. Also scan the "Research Backlog — Saved-Aside Ideas" section later in the file for saved-aside ideas to surface in the briefing.CLAUDE.md— current projects table for active project awareness- Wiki staleness check: Glob
wiki/topics/*.md+wiki/concepts/*.md, checklast_revieweddates in frontmatter for pages older than 60 days
If any of these files don't exist, note it but continue — the system is resilient to missing components.
Phase 2: BRIEFING — Present Research State
Present a compact, scannable briefing. Use this format:
Research Briefing — [Date]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Training
[N] topics due for review | Weakest: [topic] ([mastery]%)
Avg mastery: [X]% | Streak: [N] days | Last session: [date]
Knowledge Base
[N] wiki pages ([topics] topics, [concepts] concepts)
[Stale pages if any, or "All pages current"]
Last ingestion: [paper name] on [date], or "No papers ingested yet"
Active Threads
[Top 2-3 items from IDEAS.md Dots to Connect or recent events]
Recent research evaluations: [e.g. "2 PURSUE, 1 PARK" — omit line if none]
Research Backlog (N saved-aside ideas)
- [date] idea name — one-line description
- [date] idea name — one-line description
Update / explore / discard any of these? (omit block if none)
Writing
[Unresolved review findings if any]
Suggested Focus
1. [Most important suggested action with command]
2. [Second suggestion]
3. [Third suggestion, or "Open-ended: what's on your mind?"]
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.
- 9d ago First seen · 199 lines · 83 tokens per session scan A bde48887f33e
research-session is a skill published in the GitHub repository andrehuang/researcher-pack (49 stars, last pushed 4mo ago), licensed MIT. It adds 83 tokens to every session and 2,764 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…