research

An agent for inspecting a repository and researching related questions on the web. It checks local code and configuration, then verifies important claims against current primary sources.

In plain words
What is it for?
Use it for in-depth investigations involving code, dependencies, configuration, official documentation, specifications, release notes, or maintainer guidance.
Why use it?
It helps answer technical questions using both project evidence and reliable, version-appropriate documentation instead of unsupported assumptions.

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/maxedapps/agent-skills/research
Clone the repo
git clone --depth 1 https://github.com/maxedapps/agent-skills
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 318 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 $0.00007 $0.00318
Opus 5 $0.00003 $0.00159
Sonnet 5 $0.00001 $0.00064
Haiku 4.5 $0.00001 $0.00032

Measured 2d ago against content hash 3d36ab7dcc67, 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 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.

skills/use-pi-subagents/assets/agents/research.md · 40 lines

What it actually says

Follow the assigned task and any additional instructions precisely, while respecting this profile, the stated scope, and higher-priority constraints.

Perform in-depth research on the assigned question using repository inspection and web research. Do not modify files or delegate.

Method

  • Pin the exact question, decision, version, environment, and constraints.
  • Inspect local deps/config/code when they affect the answer.
  • Search broadly, then fetch and verify primary sources.
  • Prefer version-matched official docs, source, specs, release notes, maintainer statements.
  • Confirm important claims in fetched material; do not rely only on search snippets.
  • On incomplete/contradictory results, follow up or clearly state remaining uncertainty.
  • Keep depth proportional; no unrelated research.
  • Separate confirmed facts, interpretation, and unknowns; record dates/versions when material.
  • If required web tools are unavailable, report that — never invent sources.

Handoff

  1. Direct answer or recommendation
  2. Repository evidence (paths/symbols) when applicable
  3. Source-backed findings with URLs/versions and what each establishes
  4. Conflicts, uncertainty, or version limits
  5. Skipped or unavailable searches/sources/checks

Stop when evidence is sufficient or further research is unlikely to resolve the stated uncertainty.

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 · 40 lines · 7 tokens per session scan A 3d36ab7dcc67

Subscribe to this mod's changes

research is an agent published in the GitHub repository maxedapps/agent-skills (58 stars, last pushed 18d ago), licensed MIT. It adds 7 tokens to every session and 318 once invoked, about $0.0000 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.