research-curator

research-curator is a skill for Claude Code from Jamie-BitFlight/claude_skills. It costs 94 tokens per session (5,310 once invoked), scanned A, original, MIT.

A manager for research entries stored in a project’s ./research/ folder. It can create entries, import several sources, refresh old material, and check that entries follow the required structure.

In plain words
What is it for?
Use it when adding a tool or library, researching a URL, refreshing existing research, importing multiple URLs, or validating entries.
Why use it?
It removes repetitive maintenance work and helps keep a research library complete and consistently organized.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./research/.

Good fit Use it when adding a tool or library, researching a URL, refreshing existing research, importing multiple URLs, or validating entries.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills
agentmods
npx agentmods add skills/jamie-bitflight/claude_skills/research-curator

Made for: Claude Code.

Wrote 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.

agentmods badge for research-curator

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/research-curator/github.svg)](https://agentmods.dev/skills/jamie-bitflight/claude_skills/research-curator)
Your own site
<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/research-curator"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/research-curator/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.

agentmods 80×15 button for research-curator

Your own site · 80×15
<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/research-curator"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/research-curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,310 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 526
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.05310
Opus 5 $0.00047 $0.02655
Sonnet 5 $0.00019 $0.01062
Haiku 4.5 $0.00009 $0.00531

Measured 8d ago against content hash ef369484c459, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

research-curator 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 8d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/backlink_lib.py, scripts/fix_research_formatting.py, scripts/migrate_to_yaml_frontmatter.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/research-curator/SKILL.md · 527 lines

How it starts

The opening of the file, as written. The whole thing — 527 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<mode_args>$ARGUMENTS</mode_args>

[!IMPORTANT] When provided a process map or Mermaid diagram, treat it as the authoritative procedure. Execute steps in the exact order shown, including branches, decision points, and stop conditions. A Mermaid process diagram is an executable instruction set. Follow it exactly as written: respect sequence, conditions, loops, parallel paths, and terminal states. Do not improvise, reorder, or skip steps. If any node is ambiguous or missing required detail, pause and ask a clarifying question before continuing. When interacting with a user, report before acting the interpreted path you will follow from the diagram, then execute.

Research Curator -- Multi-Mode Orchestrator

Orchestrate research entry creation, maintenance, and validation in ./research/. Spawns @research-curator agents for content work; handles coordination, README updates, and post-actions.


Mode Routing

Parse <mode_args/> to select operating mode. Optional --layer 0|1|2 filters discovery by SDLC layer when used with knowledge-explorer or refresh-research.

The following diagram is the authoritative procedure for mode routing. Execute steps in the exact order shown, including branches, decision points, and stop conditions.

flowchart TD
    Start(["Parse <mode_args/>"]) --> Q1{"Does <mode_args/> contain --batch?"}
    Q1 -->|"Yes — batch flag present"| Q1Layer{"Does <mode_args/> also contain --layer 0, 1, or 2?"}
    Q1 -->|"No — batch flag absent"| Q2{"Does <mode_args/> contain --rerun?"}
    Q1Layer -->|"Yes — layer filter present"| BatchLayer(["Execute Batch Mode with layer filter applied"])
    Q1Layer -->|"No — no layer filter"| Batch(["Execute Batch Mode"])
    Q2 -->|"Yes — rerun flag present"| Q2Layer{"Does <mode_args/> also contain --layer 0, 1, or 2?"}
    Q2 -->|"No — rerun flag absent"| Q3{"Does <mode_args/> contain --validate?"}
    Q2Layer -->|"Yes — layer filter present"| RerunLayer(["Execute Rerun Mode with layer filter applied"])
    Q2Layer -->|"No — no layer filter"| Rerun(["Execute Rerun Mode"])
    Q3 -->|"Yes — validate flag present"| Validate(["Execute Validate Mode"])
    Q3 -->|"No — no flags matched — <mode_args/> contains a URL only"| Default(["Execute Default Mode — single URL"])

Read the full file on GitHub · 527 lines

Changes

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.

  1. 8d ago First seen · 527 lines · 94 tokens per session scan A ef369484c459

Subscribe to this mod's changes

research-curator is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 5,310 once invoked, about $0.0005 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 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens