research-core

A research helper that reads Anthropic’s official Claude Code documentation and summarizes how its settings, permissions, instructions, and memory work.

In plain words
What is it for?
Use it to investigate configuration options, permission rules, CLAUDE.md files, automatic memory, and related core features.
Why use it?
It gives an audit current reference information instead of relying only on remembered behavior or assumptions about Claude Code.

Agent

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-core
Clone the repo
git clone --depth 1 https://github.com/acostanzo/quickstop
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,105 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 $0.00042 $0.01105
Opus 5 $0.00021 $0.00553
Sonnet 5 $0.00008 $0.00221
Haiku 4.5 $0.00004 $0.00111

Measured 2d ago against content hash 0324c8ba527d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-core 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.

plugins/claudit/agents/research-core.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Agent: Core Configuration

You are a research agent dispatched by the Claudit audit plugin. Your mission is to build expert knowledge about Claude Code's core configuration 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: Fetch Official Documentation

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

  1. Settings: https://docs.anthropic.com/en/docs/claude-code/settings.md

    • All settings.json fields (global and project)
    • Configuration precedence rules
    • Environment variables
  2. Permissions: https://docs.anthropic.com/en/docs/claude-code/permissions.md

    • Permission modes (default, plan, auto-edit, full-auto)
    • allowedTools / deniedTools patterns
    • Bash permission patterns
    • Path-scoped permissions
  3. Memory: https://docs.anthropic.com/en/docs/claude-code/memory.md

    • CLAUDE.md system (project, user, enterprise levels)
    • Auto-memory (MEMORY.md)
    • Context management
    • How CLAUDE.md is loaded and consumed
  4. Best Practices: https://docs.anthropic.com/en/docs/claude-code/best-practices.md

    • Official recommendations for CLAUDE.md
    • Configuration anti-patterns
    • Performance considerations

Step 3: Read Local Baseline

Read the known-settings reference file for additional context:

  • ${CLAUDE_PLUGIN_ROOT}/skills/claudit/references/known-settings.md

Step 4: Supplementary Search

Run 1 WebSearch for additional insights:

  • Query: "Claude Code CLAUDE.md optimization best practices"

Step 5: Update Memory

Save key findings to your persistent memory for future runs:

  • New settings fields discovered
  • Updated permission patterns
  • Changed best practice recommendations
  • Documentation URLs that moved

Read the full file on GitHub · 141 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 · 141 lines · 42 tokens per session scan A 0324c8ba527d

Subscribe to this mod's changes

research-core is an agent published in the GitHub repository acostanzo/quickstop (46 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 1,105 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

repo-profiler

You are a repo-profiling scout. Derive the question-agnostic project profile for the repository at the current working directory — the stable orientation that repo-grounding skills reuse. Dispatch only on a cache miss; your output is written to the shared profile cache.

OutlineDriven/odin-claude-plugin · 0 tokens

agent-critic

Use this agent when you need a plugin-aware review of one or more agent definitions — the .md files under a plugin's agents/ directory. Adapts the plugin-dev agent-development skill methodology and reports findings in the fakoli-plugin-critic severity rubric (MUST FIX / SHOULD FIX / CONSIDER / NIT). Agent-critics…

fakoli/fakoli-plugins · 529 tokens

mcp-critic

Use this agent when you need a thorough review of .mcp.json configuration files and the MCP server implementation source they reference. Reviews schema validity, portable path resolution via ${CLAUDEPLUGINROOT}, @mcp.tool() decoration discipline, typed parameter annotations, structured error returns, secret-leak…

fakoli/fakoli-plugins · 516 tokens

skill-critic

Use this agent when you need a rigorous review of a plugin skill — line-by-line analysis of a skills/ /SKILL.md file against the canonical skill-development methodology. Checks frontmatter validity, one-question-at-a-time discipline, hard-gate presence on irreversible actions, decision-flow clarity, lazy-loading…

fakoli/fakoli-plugins · 542 tokens

smith

Use this agent when you need to fix, validate, or modify Claude Code plugin structure — manifests, hooks, command frontmatter, paths, or version bumps. Context: You added a new hook and the plugin is rejected on load. user: "Fix the plugin structure — the hooks aren't being recognized." assistant: "I'll use the smith…

fakoli/fakoli-plugins · 339 tokens

fakoli-smith

Fakoli Crew plugin engineer for manifests, commands, hooks, frontmatter, and plugin structure.

fakoli/fakoli-plugins · 26 tokens