agentmods.dev

research

research is a command for coding agents from koolamusic/claudefiles. It costs 36 tokens per session (1,310 once invoked), scanned A, original, MIT.

A sprint research command that gathers information about a planned software task and saves the findings for later planning. A sprint is a defined batch of development work.

In plain words
What is it for?
Use it to start a sprint, research a free-text task or GitHub issue, create the sprint files, and produce a research document.
Why use it?
It reduces guesswork by checking the codebase, existing patterns, related external information, and project context before implementation is planned.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the jira plugin — 13 commands, 9 agents shipped together

not rated 132 5d ago A scan 36 tokens original MIT
View the source file koolamusic/claudefiles
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 commands/koolamusic/claudefiles/research
Clone the repo
git clone --depth 1 https://github.com/koolamusic/claudefiles

Or install jira, the plugin that ships this one along with the rest of its 13 commands, 9 agents.

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/commands/koolamusic/claudefiles/research.svg)](https://agentmods.dev/commands/koolamusic/claudefiles/research)
Your own site
<a href="https://agentmods.dev/commands/koolamusic/claudefiles/research"><img src="https://agentmods.dev/badge/commands/koolamusic/claudefiles/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,310 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 $0.00036 $0.01310
Opus 5 $0.00018 $0.00655
Sonnet 5 $0.00007 $0.00262
Haiku 4.5 $0.00004 $0.00131

Measured 4d ago against content hash c1be35f1faec, 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 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.

plugins/jira/commands/research.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Begin a sprint. The first deliverable is RESEARCH.md. Subsequent commands are /jira:plan then /jira:execute.

Parse the input

$ARGUMENTS is one of:

  • A free-text problem statement, e.g. add rate limiting to /api/login
  • --issue <N> — pull a GitHub issue as the sprint brief

If empty, use AskUserQuestion to ask what the user wants to work on. Don't proceed without a brief.

Steps

  1. Verify .jira/ exists. If not, run /jira:init semantics yourself (or tell the user to).

1.5. Read project context. Check for .project/PROJECT.md and .project/ROADMAP.md. If either exists, include them as context for all researcher agents — project goals, constraints, and roadmap phases shape what's worth researching (e.g. don't research features explicitly deferred in the roadmap). Pass the paths to each researcher in step 5.

  1. Build the sprint slug: YYYY-MM-DD-<short-kebab-from-brief>. Slug ≤ 40 chars, lowercase, alphanumeric + hyphens. Use date -u +%Y-%m-%d.

  2. Create the sprint directory: .jira/sprints/<slug>/. If a date+slug collision, append -2, -3, etc.

  3. Write BRIEF.md at .jira/sprints/<slug>/BRIEF.md:

    • If --issue N: run gh issue view N --json title,body,url,labels,state and use the JSON to populate the template at ${CLAUDE_PLUGIN_ROOT}/templates/sprint/BRIEF.md. Include the URL in the Issue: field.
    • If free text: populate the template directly. Don't expand the user's words; record them.

  4. Spawn three jira-researcher agents in parallel (single message, three Agent tool calls). Each gets:

    • The sprint slug
    • The brief path
    • One focus area: codebase, patterns, external
    • An output path: .jira/sprints/<slug>/research-<focus>.md

    The agents will also pick up .jira/sprints/<slug>/CONTEXT.md if it exists (it doesn't, on first pass — but the convention holds for re-research).

  5. Synthesize. When all three return, read the three research-<focus>.md files and write .jira/sprints/<slug>/RESEARCH.md using the template at ${CLAUDE_PLUGIN_ROOT}/templates/sprint/RESEARCH.md. Don't paraphrase the per-focus files into oblivion — keep their headlines and citations.

Read the full file on GitHub · 91 lines

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 · 91 lines · 0 tokens per session scan A c1be35f1faec

Subscribe to this mod's changes

research is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 5d ago), licensed MIT. It adds 36 tokens to every session and 1,310 once invoked, about $0.0002 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.

Project managementResearch
Related

Other commands, from other repositories

project-recap

Generate a visual project recap for context switching.

nicobailon/visual-explainer · 12 tokens

os-meeting

快速创建和管理AI团队会议.

CronusL-1141/AI-company · 11 tokens

workspace

Testany Workspace, 管理工作空间，成员权限，团队组织.

TestAny-io/testany-agent-skills · 14 tokens

standup

Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.

skullninja/coco-workflow · 21 tokens

m-task-planner

Target: $ARGUMENTS (Default: requirement document(s) discovered in the project).

penwyp/ClaudePreference · 0 tokens

triage-issues

Launch the Issue Triage Agent (Haiku) to categorize and prioritize GitHub issues.

rshade/mcp-devtools-server · 0 tokens