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 zhouyou-gu/skill-marketplace-template --skill research-goal-curatorgit clone --depth 1 https://github.com/zhouyou-gu/skill-marketplace-templateWrote 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/zhouyou-gu/skill-marketplace-template/research-goal-curator)<a href="https://agentmods.dev/skills/zhouyou-gu/skill-marketplace-template/research-goal-curator"><img src="https://agentmods.dev/badge/skills/zhouyou-gu/skill-marketplace-template/research-goal-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.
<a href="https://agentmods.dev/skills/zhouyou-gu/skill-marketplace-template/research-goal-curator"><img src="https://agentmods.dev/badge/skills/zhouyou-gu/skill-marketplace-template/research-goal-curator.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 | $0.00078 | $0.00908 |
| Opus 5 | $0.00039 | $0.00454 |
| Sonnet 5 | $0.00016 | $0.00182 |
| Haiku 4.5 | $0.00008 | $0.00091 |
Grade A, and why
research-goal-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 12d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Goal Curator
Trigger
- Use when a workspace already contains
AGENT_GOAL.mdand the user wants to refine, clarify, or save a research goal. - Use when the user has a research brief, chat history, or tentative wording that should be turned into an internally consistent goal file.
- Do not use this skill to scaffold AGENT files. If
AGENT_GOAL.mddoes not exist, route to the appropriate scaffolder:agent-filesfor generic workspaces ormanuscript-writing-agent-filesfor LaTeX IEEE manuscript writing. - Do not use this skill to rewrite
AGENT.md,AGENT_HARNESS.md, orAGENT_PROGRESS.md; its write surface is onlyAGENT_GOAL.md.
Inputs
target_dir: workspace directory expected to containAGENT_GOAL.mdresearch_brief: concise statement of the research intent to preserve and refine into durable goal-file contentchat_context: optional conversation excerpts, notes, or prior wording; supporting context only, not persistent scope unless explicitly approved as goal-file contentdry_run: when true, return a structured preview without writing
Workflow
- Verify that
target_dir/AGENT_GOAL.mdexists. If it does not, stop and tell the caller to scaffold the workspace first with the appropriate scaffolder (agent-filesfor generic workspaces ormanuscript-writing-agent-filesfor LaTeX IEEE manuscript writing). - Read the existing
AGENT_GOAL.mdand identify its current sections: statement, scope, non-goals, success criteria, and constraints. - Read
research_briefand anychat_context, then interact with the user until the research intention is explicit enough to save. Treat chat context as evidence for wording and intent; do not turn it into persistent scope, non-goals, success criteria, or constraints unless the user explicitly approves that content forAGENT_GOAL.md. - When the user has already approved exact wording, preserve that wording unless the user explicitly asks for a revision.
- Curate the whole
AGENT_GOAL.mdso the sections are mutually consistent and reflect the same research intention. Preserve neutral scaffold entries such as "Not yet specified by user" only when the user has not approved durable content for that section; replace them deliberately when the user approves concrete section content. - If
dry_runis true, return the proposed update summary without writing. Otherwise updateAGENT_GOAL.mdand return a concise report of what changed.
What ships with it
7 files 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.
- 12d ago First seen · 55 lines · 78 tokens per session scan A cef7facf9559
research-goal-curator is a skill published in the GitHub repository zhouyou-gu/skill-marketplace-template (5 stars, last pushed 19d ago), licensed MIT. It adds 78 tokens to every session and 908 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 2026-08-31.
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…
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…
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…