research

research is a skill for Claude Code, Codex from orin-dx/agent-plugins. It costs 170 tokens per session (692 once invoked), scanned A, original, MIT.

A research workflow that investigates a question by mapping relevant sources, reading them, combining the findings, and reviewing risks. It can use internal project material, external references, or both depending on the question.

In plain words
What is it for?
Use it to understand how a codebase works, compare possible approaches, investigate prior art, or assess risks before writing a specification or plan.
Why use it?
It gives a defined path from an unclear question to evidence-based findings. This helps avoid making plans without first checking existing code, documents, dependencies, or prior work.

Skill for Claude CodeCodex

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/orin-dx/agent-plugins/research
Any agent
npx skills add orin-dx/agent-plugins --skill research
Clone the repo
git clone --depth 1 https://github.com/orin-dx/agent-plugins

Made for: Claude Code, Codex.

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/orin-dx/agent-plugins/research.svg)](https://agentmods.dev/skills/orin-dx/agent-plugins/research)
Your own site
<a href="https://agentmods.dev/skills/orin-dx/agent-plugins/research"><img src="https://agentmods.dev/badge/skills/orin-dx/agent-plugins/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 692 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 $0.00170 $0.00692
Opus 5 $0.00085 $0.00346
Sonnet 5 $0.00034 $0.00138
Haiku 4.5 $0.00017 $0.00069

Measured 3d ago against content hash 73aa3196acff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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/vanguard/skills/research/SKILL.md · 45 lines

What it actually says

Vanguard Research Skill

One skill, one pipeline — not a menu of separately-invokable modes. recon maps sources (internal specs/docs/code, dependency manifests, external references), reader reads only what the map points at, synthesizer resolves the findings into one report, risk-assessor reviews the resulting approach. The pipeline narrows itself to what's asked: a question answerable from internal sources alone gets scope: internal from recon and never touches external search; a request for risk review of an already-decided approach can hand risk-assessor that approach directly.


<language_agnostic_note> Recon detects the workspace language from manifest files present (Cargo.toml → Rust, package.json → Node/TypeScript, pyproject.toml → Python, etc.), then loads the appropriate shared/references search heuristics for that ecosystem. The skill is not language-specific. </language_agnostic_note>


<subagent_dispatch_matrix>

Agent Role Model / Effort Delegate When
recon Source mapper haiku / low Start every research task here. Maps internal sources, external keywords, and existing implementations.
reader Evidence extractor sonnet / medium Given the source map, reads each source and extracts findings with citations and confidence levels.
synthesizer Recommendation producer sonnet / medium Given findings, synthesizes a research-report@1 with a falsifiable recommendation and confidence level.
risk-assessor Risk prioritizer sonnet / medium Given a proposed approach or research-report@1, identifies and prioritizes technical risks with mitigations.

</subagent_dispatch_matrix>


The recommendation is falsifiable: a spec or plan written from it will not be surprised by implementation reality.

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. 3d ago First seen · 45 lines · 170 tokens per session scan A 73aa3196acff

Subscribe to this mod's changes

research is a skill published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed today), licensed MIT. It adds 170 tokens to every session and 692 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

campus-assignment-cleaner

Activates when a student or campus developer needs to make a working-but-messy codebase submission-ready before uploading it for grading. Trigger phrasings include "clean up my assignment before submitting", "remove debug prints and commented code", "tidy this up before I upload it to Moodle/Canvas/GitHub Classroom"…

ieeecsopen/mcp-cs · 158 tokens

git-workflow-and-versioning

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…

addyosmani/agent-skills · 74 tokens

advogado-criminal

Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.

sickn33/agentic-awesome-skills · 42 tokens

agent-evaluation-reporting

Use when summarizing agent evaluations where autonomous, assisted, failed, timed-out, or invalid outcomes must remain distinct and comparable.

sickn33/agentic-awesome-skills · 31 tokens

agent-orchestration-multi-agent-optimize

Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.

sickn33/agentic-awesome-skills · 38 tokens

adhx

Fetch any X/Twitter post as clean LLM-friendly JSON. Converts x.com, twitter.com, or adhx.com links into structured data with full article content, author info, and engagement metrics. No scraping or browser required.

sickn33/agentic-awesome-skills · 49 tokens