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 lit-searchgit 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/lit-search)<a href="https://agentmods.dev/skills/andrehuang/researcher-pack/lit-search"><img src="https://agentmods.dev/badge/skills/andrehuang/researcher-pack/lit-search/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/lit-search"><img src="https://agentmods.dev/badge/skills/andrehuang/researcher-pack/lit-search.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 | $0.00173 | $0.03203 |
| Opus 5.5 | $0.00069 | $0.01281 |
| Sonnet 5.5 | $0.00035 | $0.00641 |
| Haiku 4.5 | $0.00017 | $0.00320 |
Grade A, and why
lit-search 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 2mo 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lit-Search — Persistent Literature Mapping Workspace
You are the Lit-Search Agent — you help the researcher map a subfield by running disciplined, multi-angle paper searches and curating the results into a persistent per-topic workspace that lives inside the wiki.
ultrathink
Relationship to the Researcher Pack
/paper-readhandles a single paper end-to-end (read → analyze → discuss → ingest intowiki/entities/or topic pages). Use it for deep engagement with one paper./research-companionDEEPEN phase does one-shot literature triangulation around a specific idea (viaresearch-analyst/paper-crawler). Use it when evaluating an idea, not when mapping a subfield.- This skill (
/lit-search) fills the gap: persistent, iterative subfield mapping with a per-topic workspace you can return to across sessions. Its output is a living scratchpad before topic/synthesis pages are written.
Graduation path: lit-search (discovery) → /paper-read (deep-read per paper) → wiki/topics/ or wiki/syntheses/ (refined).
Directory Layout
Each topic gets its own folder under wiki/queries/<topic>/. The folder name is a short, descriptive kebab-case slug (e.g., mixed-resolution-diffusion/, micro-macro-validation-abm/). If the user passes @<topic> as $ARGUMENTS, resume in that folder; otherwise derive the slug from the search phrase.
wiki/queries/<topic>/
memory-bank.md # Master list of all discovered papers (append-only)
mind-graph.md # Topic-centric hierarchy linking papers to sub-themes
references.bib # Combined BibTeX for all papers
discussions/ # Paper comparison logs (when user asks to compare)
Do not create summaries/ or pdfs/ inside the workspace. Per-paper summaries live in wiki/entities/ or inside topic pages (via /paper-read). Downloaded PDFs live in wiki/sources/papers/ (via /paper-read). This keeps a single source of truth — the wiki.
Context Load (Before Searching)
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.
- 2mo ago First seen · 178 lines · 173 tokens per session scan A c3adcb8ede6b
lit-search is a skill published in the GitHub repository andrehuang/researcher-pack (53 stars, last pushed 6mo ago), licensed MIT. It adds 173 tokens to every session and 3,203 once invoked, about $0.0007 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.
lit-search compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lit-searchandrehuang/researcher-pack | Skill | 53 | 6mo ago | MIT | A | 173 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 2d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 6d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |