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 julianobarbosa/claude-code-skills --skill research-outlinegit clone --depth 1 https://github.com/julianobarbosa/claude-code-skillsWrote 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/julianobarbosa/claude-code-skills/research-outline)<a href="https://agentmods.dev/skills/julianobarbosa/claude-code-skills/research-outline"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/research-outline/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/julianobarbosa/claude-code-skills/research-outline"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/research-outline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00106 | $0.01558 |
| Opus 5 | $0.00053 | $0.00779 |
| Sonnet 5 | $0.00021 | $0.00312 |
| Haiku 4.5 | $0.00011 | $0.00156 |
Grade A, and why
research-outline 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.
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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research — Preliminary Research
Bootstraps a research project. Produces the outline (items + execution config) and field schema (the research dimensions) that /research-deep and /research-report consume.
Trigger
/research-outline <topic>
Pipeline contract
This skill is the entry point of a four-step pipeline:
/research-outline <topic> # this skill — produces outline.yaml + fields.yaml
├─ /research-add-items # optional — append more research objects
├─ /research-add-fields # optional — append more research dimensions
├─ /research-deep # fan-out per-item deep research → results/*.json
└─ /research-report # summarise results into a markdown report
Output layout:
{current_working_directory}/{topic_slug}/
├── outline.yaml # items list + execution config
└── fields.yaml # field definitions
Workflow
Step 1 — Generate initial framework from model knowledge
Based on the topic, use the model's existing knowledge to draft:
- a main research-objects (items) list in the domain
- a suggested research-field framework
Show the draft as {step1_output}, then AskUserQuestion to confirm:
- Need to add or remove items?
- Does the field framework match what they want to learn?
Step 2 — Web-search supplement
AskUserQuestion for the time range (e.g. last 6 months, since 2024, unlimited).
Parameters captured at this point:
{topic}— the user's research topic{YYYY-MM-DD}— today's date{step1_output}— full output from Step 1{time_range}— user's chosen window
Launch one background research agent via the Task tool with subagent_type: general-purpose (or your project's research subagent if one is registered).
Why the prompt below is templated literally: the subagent runs in isolation without the conversation's context. Its prompt has to carry every parameter explicitly, and small wording changes ("supplement" vs "add") subtly change how aggressively it searches. Treat the template as a stable contract — replace {xxx} variables and keep the rest as-is so results stay comparable across runs.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 183 lines · 106 tokens per session scan A e18803dd73ed
research-outline is a skill published in the GitHub repository julianobarbosa/claude-code-skills (10 stars, last pushed 16d ago), licensed MIT. It adds 106 tokens to every session and 1,558 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.
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…
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…
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…