research

research is a skill for Claude Code from TheWinci/mimirs. It costs 88 tokens per session (491 once invoked), scanned A, original, Apache-2.0.

A project-research skill for answering difficult questions by combining source code, project structure, version history, recorded decisions, and discussions.

In plain words
What is it for?
Use it for deep, cross-cutting investigations that require searching code, tracing relationships, checking history, and supporting conclusions with project sources.
Why use it?
It helps explain how a project works when the answer is spread across many files and past changes rather than documented in one place.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mimirs plugin — 11 skills, 3 hooks shipped together

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 skills/thewinci/mimirs/research
Any agent
npx skills add TheWinci/mimirs --skill research
Clone the repo
git clone --depth 1 https://github.com/TheWinci/mimirs

Made for: Claude Code.

Or install mimirs, the plugin that ships this one along with the rest of its 11 skills, 3 hooks.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/thewinci/mimirs/research.svg)](https://agentmods.dev/skills/thewinci/mimirs/research)
Your own site
<a href="https://agentmods.dev/skills/thewinci/mimirs/research"><img src="https://agentmods.dev/badge/skills/thewinci/mimirs/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 491 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 5.1 $0.00088 $0.00491
Opus 5 $0.00044 $0.00246
Sonnet 5 $0.00018 $0.00098
Haiku 4.5 $0.00009 $0.00049

Measured 6d ago against content hash 804bfcf3673b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

research 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 6d 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.

skills/research/SKILL.md · 19 lines

What it actually says

Research

Goal: a thorough, cited answer to a specific question — pulled from across the whole project memory, not one file or one area. Where explore maps an area's structure, research answers a question by combining code, history, decisions, and discussion.

  1. Frame the question — break it into the sub-questions you must answer. State them, so the synthesis can be checked against them at the end.
  2. The codesearch "<sub-question>" for the relevant files, then read_relevant "<behavior>" for the actual functions/sections with line ranges. Use the extensions/dirs/excludeDirs filters to scope. search_symbols <name> for named things you already know.
  3. How it connects — when the question is about relationships: project_map(focus: <file>), depends_on/dependents <file>, impact <symbol> (transitive callers), trace from=<a> to=<b> (how one reaches another).
  4. History & whysearch_commits "<topic>" for why and when it changed; file_history <file> for how a file evolved.
  5. Decisions & discussionsearch_checkpoints "<topic>" for recorded decisions and direction changes; search_conversation "<topic>" for the back-and-forth and alternatives considered.
  6. Caveatsget_annotations (search across notes) for known bugs, constraints, and fragile spots that qualify the answer.
  7. Verify — before asserting any claim, reopen the cited source and confirm it. Don't synthesize from snippets alone.

Finish: answer each sub-question in plain language with a file:line, commit, or checkpoint citation; separate what the source proves from what is inferred; list what stayed unresolved instead of guessing.

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. 6d ago First seen · 19 lines · 88 tokens per session scan A 804bfcf3673b

Subscribe to this mod's changes

research is a skill published in the GitHub repository TheWinci/mimirs (29 stars, last pushed 21d ago), licensed Apache-2.0. It adds 88 tokens to every session and 491 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 2026-08-30.

Related

Other skills, from other repositories

memorix-troubleshooting

Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.

AVIDS2/memorix · 36 tokens

memorix-sessions

Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.

AVIDS2/memorix · 31 tokens

azure-event-grid-webhooks

Receive and validate Azure Event Grid webhook deliveries. Use when setting up an Event Grid WebHook event handler, implementing the Microsoft.EventGrid.SubscriptionValidationEvent handshake (echo data.validationCode as validationResponse with HTTP 200), implementing the CloudEvents v1.0 HTTP OPTIONS abuse-protection…

hookdeck/webhook-skills · 148 tokens

baselinker-webhooks

Receive BaseLinker (Base.com) webhooks. Use when building a BaseLinker order or warehouse callback receiver, because BaseLinker is not a normal webhook source: deliveries arrive as HTTP HEAD requests with NO body, the entire payload is in the query string (observed params: orderid, state), there is NO signature…

hookdeck/webhook-skills · 131 tokens

clio-webhooks

Receive and verify Clio (Clio Manage) webhooks. Use when setting up Clio webhook handlers, debugging X-Hook-Signature verification, completing the X-Hook-Secret handshake, or handling legal practice events like matter.created, contact.updated, activity.created, or bill events.

hookdeck/webhook-skills · 64 tokens

favro-webhooks

Receive and verify Favro webhooks. Use when setting up Favro webhook handlers, debugging X-Favro-Webhook signature verification, accepting the setup ping, or handling card events (card.created, card.committed, card.moved, card.updated, card.deleted) and comment events (comment.created, comment.updated…

hookdeck/webhook-skills · 121 tokens