research

A technical research workflow for investigating documentation, recommended practices, and difficult engineering questions. It checks official documentation first and adds recent technical sources when needed.

In plain words
What is it for?
Use it to verify how a library works, compare implementation practices, investigate a complex bug, or review recent technology changes.
Why use it?
It reduces the need to search several sources manually and helps organise findings into a reasoned answer with sources.

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

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 661 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 $0.00025 $0.00661
Opus 5 $0.00013 $0.00331
Sonnet 5 $0.00005 $0.00132
Haiku 4.5 $0.00003 $0.00066

Measured yesterday against content hash 6d9ec45c63eb, 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 yesterday.

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/ai-pilot/skills/research/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source priority is always official docs (Context7) first, recent tutorials (Exa, <6 months) second, older content only with version verification. It runs in a forked context via the research-expert agent.

Session: ${CLAUDE_SESSION_ID}

Research Topic: $ARGUMENTS

Research Skill

Research Workflows

Standard Query

1. THINK → Sequential Thinking decomposition
2. RESOLVE → Context7 resolve-library-id
3. DOCUMENT → Context7 query-docs (5000-10000 tokens)
4. SUPPLEMENT → Exa code context search
5. SYNTHESIZE → Structured answer with sources

Complex Investigation

1. DEEP THINK → Multi-hypothesis Sequential Thinking
2. DEEP RESEARCH → Exa deep researcher (45s-2min)
3. MONITOR → Check status until completed
4. VALIDATE → Cross-check Context7 official sources
5. REPORT → Comprehensive solution

Technology Trends

1. WEB SCAN → Exa search latest developments
2. CODE PATTERNS → Exa code context for practices
3. ECOSYSTEM → Company research for key players
4. ANALYSIS → Sequential Thinking for implications
5. RECOMMENDATIONS → Actionable insights

Multi-Source Synthesis

Parallelization:

  • Run resolve-library-id + web_search_exa simultaneously
  • Launch multiple Exa searches concurrently
  • Execute Context7 docs + Exa code search in parallel

Source Priority:

  1. Official documentation (Context7)
  2. Recent tutorials (Exa, <6 months)
  3. Older content (with version verification)

Read the full file on GitHub · 83 lines

Files

What ships with it

2 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.

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. yesterday First seen · 83 lines · 25 tokens per session scan A 6d9ec45c63eb

Subscribe to this mod's changes

research is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed 28d ago), licensed MIT. It adds 25 tokens to every session and 661 once invoked, about $0.0001 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.