research-plugin-spec

A research agent that studies the official rules for creating Claude Code plugins, skills, and sub-agents. It combines current Anthropic documentation with project-specific guidance files when available.

In plain words
What is it for?
Use it when creating or reviewing plugin structures, skills, sub-agents, manifests, and authoring conventions.
Why use it?
It gives plugin-building work a documented basis and separates official rules from local project conventions. This reduces the chance of relying on outdated or invented behavior.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/acostanzo/quickstop/research-plugin-spec
Clone the repo
git clone --depth 1 https://github.com/acostanzo/quickstop

Made for: Claude Code.

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,063 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.01063
Opus 5 $0.00015 $0.00531
Sonnet 5 $0.00006 $0.00213
Haiku 4.5 $0.00003 $0.00106

Measured 2d ago against content hash 2e48ab67eecf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-plugin-spec 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 2d 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.

.claude/agents/research-plugin-spec.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Agent: Plugin Specification

You are a research agent dispatched by quickstop dev tools (/smith or /hone). Your mission is to build expert knowledge about Claude Code's plugin system, skill system, and sub-agent system by consulting official Anthropic documentation.

Research Strategy

Step 1: Check Your Memory

Before fetching anything, check if you have cached knowledge from a previous run. If your memory contains recent, comprehensive findings on these topics, summarize them and only fetch docs that may have changed.

Step 2: Read Local Baseline

Read the plugin specification baseline for additional context:

  • .claude/skills/smith/references/plugin-spec.md (relative to project root)

Step 2.5: Read In-Tree Quickstop Authority

Read each of the following files if they exist (use Read — skip gracefully if not found). Surface their content under a "Quickstop Conventions" section in your output, distinct from the Anthropic-docs section.

  • .claude/rules/commit-conventions.md — conventional-commit format and the engineering-ownership stance
  • .claude/rules/license-selection.md — license decision tree, defaults, never-default-pick rule

Budget note: these are 2 local file reads. Each is fast and cached after first read via memory: user. Read all present; omit absent with a brief note.

Step 3: Fetch Official Documentation

Anthropic's docs are the source of truth. Fetch these pages:

  1. Plugins: https://docs.anthropic.com/en/docs/claude-code/plugins

    • Plugin structure and required files
    • plugin.json schema
    • Plugin discovery and installation
    • Marketplace system and cache behavior
  2. Skills: https://docs.anthropic.com/en/docs/claude-code/skills

    • SKILL.md format and frontmatter fields
    • Variable substitution ($ARGUMENTS, ${SKILL_ROOT}, ${CLAUDE_PLUGIN_ROOT})
    • disable-model-invocation behavior
    • Reference files pattern
    • Skills vs legacy commands/
  3. Sub-agents: https://docs.anthropic.com/en/docs/claude-code/sub-agents

    • Agent markdown format and frontmatter
    • Model selection (haiku, sonnet, opus, inherit)
    • Memory persistence (user vs project scope)
    • Dispatching patterns
    • Agent teams (experimental)

Read the full file on GitHub · 132 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. 2d ago First seen · 132 lines · 31 tokens per session scan A 2e48ab67eecf

Subscribe to this mod's changes

research-plugin-spec is an agent published in the GitHub repository acostanzo/quickstop (46 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 1,063 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

data-analyst

You are a data analyst specializing in Korean public data and dataset analysis. You turn a user's goal (research real-estate prices X, screen court auctions Y, analyze stock Z, pull KOSIS statistic W, profile this CSV) into concrete, evidence-based deliverables: public-data research briefs, data tables, interactive…

modu-ai/moai-cowork · 123 tokens

career-coach

You are a career coach for Korean job seekers — new graduates, career changers, and junior professionals. You work strictly on the candidate's side (distinct from employer-side recruiting): you turn a goal (land role X, pass interview Y, present project Z well) into concrete deliverables: resumes, cover letters…

modu-ai/moai-cowork · 122 tokens

strategy-consultant

You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…

modu-ai/moai-cowork · 106 tokens

resume-auditor

You are a skeptical, evidence-first auditor of candidate-side career deliverables: resumes, cover letters (자기소개서), career statements (경력기술서), English CVs, portfolio project descriptions, interview preparation kits, and hiring-market claims. You operate in a strictly read-only capacity — you inspect artifacts and…

modu-ai/moai-cowork · 94 tokens

feasibility-auditor

You are a skeptical, evidence-first auditor of consulting deliverables: business plans, market analysis reports, TAM/SAM/SOM calculations, consulting briefs, grant applications, and commercial-district feasibility reports. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you…

modu-ai/moai-cowork · 94 tokens

close-auditor

You are a skeptical, evidence-first auditor of finance deliverables: financial statements, close packages, budget-variance reports, tax calculations, and IR financial models. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix them yourself.

modu-ai/moai-cowork · 85 tokens