loop-research

loop-research is a skill for Claude Code, Codex from levi-qiao/longgraph-skill. It costs 85 tokens per session (518 once invoked), scanned A, original, MIT.

A structured research process for comparing technical approaches using open-source projects, original research, and controlled experiments before choosing one. It runs repeated review rounds with two independent research paths and keeps lasting evidence and audit records.

In plain words
What is it for?
Use it to compare feasible implementations, evaluate them with benchmarks or A/B tests, and select an approach before delivery or code consolidation.
Why use it?
It helps when a technical decision is uncertain and a quick search or informal comparison would not provide enough evidence.

Skill for Claude CodeCodex

Part of the longgraph plugin — 5 skills 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/levi-qiao/longgraph-skill/loop-research
Any agent
npx skills add levi-qiao/longgraph-skill --skill loop-research
Clone the repo
git clone --depth 1 https://github.com/levi-qiao/longgraph-skill

Made for: Claude Code, Codex.

Or install longgraph, the plugin that ships this one along with the rest of its 5 skills.

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 loop-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/levi-qiao/longgraph-skill/loop-research.svg)](https://agentmods.dev/skills/levi-qiao/longgraph-skill/loop-research)
Your own site
<a href="https://agentmods.dev/skills/levi-qiao/longgraph-skill/loop-research"><img src="https://agentmods.dev/badge/skills/levi-qiao/longgraph-skill/loop-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 518 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 $0.00085 $0.00518
Opus 5 $0.00043 $0.00259
Sonnet 5 $0.00017 $0.00104
Haiku 4.5 $0.00009 $0.00052

Measured 4d ago against content hash 8bcbdf1b80fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loop-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 4d 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/loop-research/SKILL.md · 37 lines

What it actually says

loop-research — a loop-graph preset for evidence-led choices

A thin authoring entry. It binds a research-and-selection pack, starts the owner interview, then follows loop-graph to compile the normal executor, ledger, directives, ops, and supervisor artifacts. It is not a research node, a second runtime, or a second template set.

Fit check

  • Use this when the approach is undecided and a decision needs comparative evidence from open-source projects, primary research, and a controlled benchmark or A/B experiment.
  • Use ../loop-deliver/SKILL.md once the approach is chosen, or ../loop-converge/SKILL.md for code consolidation.
  • For a short answer, one source lookup, or non-comparative literature summary, use the host's ordinary research task instead of a graph.

On invoke

  1. Inspect the workspace, existing evidence, experiment harnesses, data policy, and current host the same way loop-graph does. Never ask which client this is when context already identifies it.
  2. Read and bind preset.md. That pack is the North Star, supervisor requirement, interview, evidence shape, method guards, knob overrides, and artifact emphasis. Do not redesign them.
  3. Start the owner interview immediately. Ask only the pack's unresolved choices — decision/scope, evidence budget and data authority, and launch — as recommended A/B (or A/B/C) choices. Do not ask the owner to invent evaluation criteria.
  4. Read and follow ../loop-graph/SKILL.md from When called from a preset skill through generate and deliver. Compile only from loop-graph's templates/. This skill never executes the generated nodes.
Files

What ships with it

3 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. 4d ago First seen · 37 lines · 85 tokens per session scan A 8bcbdf1b80fa

Subscribe to this mod's changes

loop-research is a skill published in the GitHub repository levi-qiao/longgraph-skill (69 stars, last pushed 2d ago), licensed MIT. It adds 85 tokens to every session and 518 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

team-orchestrator

Spawn an agent team from a predefined role pool (frontend designer, backend developer, researcher, tester, refactorer). Selects the right subset based on the task. Use when the user says "/team", "spawn team", "create team", "start team", or wants to set up a multi-agent development team for a project task.

Jacky040124/claude-team-orchestrator · 74 tokens

orchestra

Run an oversized task as a parallel multi-session sprint: one conductor, several work managers in dedicated git worktrees, a file-based mailbox for coordination, watchdog supervision, and a clean teardown. Trigger: /orchestra for a new sprint, /orchestra resume to warm-boot into a running one.

ElazarKrispel/orchestra · 67 tokens

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

python-package-management

Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.

microsoft/agent-framework · 43 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

python-feature-lifecycle

Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.

microsoft/agent-framework · 43 tokens