gsd:research-phase

gsd:research-phase is a command for Claude Code from kryptobaseddev/cleo. It costs 25 tokens per session (1,398 once invoked), scanned A, original, MIT.

A standalone research workflow for investigating how to implement a planned project phase before deciding or writing the detailed plan.

In plain words
What is it for?
Use it to research libraries, implementation methods, and likely pitfalls for a specific phase.
Why use it?
It separates technical investigation from implementation decisions and helps reveal feasibility issues or alternative approaches.

Command for Claude Code

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/kryptobaseddev/cleo/research-phase
Clone the repo
git clone --depth 1 https://github.com/kryptobaseddev/cleo

Made for: Claude Code.

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 gsd:research-phase

README.md
[![agentmods](https://agentmods.dev/badge/commands/kryptobaseddev/cleo/research-phase.svg)](https://agentmods.dev/commands/kryptobaseddev/cleo/research-phase)
Your own site
<a href="https://agentmods.dev/commands/kryptobaseddev/cleo/research-phase"><img src="https://agentmods.dev/badge/commands/kryptobaseddev/cleo/research-phase.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,398 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 $0.01398
Opus 5 $0.00013 $0.00699
Sonnet 5 $0.00005 $0.00280
Haiku 4.5 $0.00003 $0.00140

Measured yesterday against content hash 60cd4356529e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gsd:research-phase 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.

Origin

Copies of this mod

3 near-identical copies found in the catalogue:

.cleo/agent-outputs/T-POMODORO-BENCH-2026-04-16/gsd/.claude/commands/gsd/research-phase.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Note: This is a standalone research command. For most workflows, use /gsd-plan-phase which integrates research automatically.

Use this command when:

  • You want to research without planning yet
  • You want to re-research after planning is complete
  • You need to investigate before deciding if a phase is feasible

Orchestrator role: Parse phase, validate against roadmap, check existing research, gather context, spawn researcher agent, present results.

Why subagent: Research burns context fast (WebSearch, Context7 queries, source verification). Fresh 200k context for investigation. Main context stays lean for user interaction.

<available_agent_types> Valid GSD subagent types (use exact names — do not fall back to 'general-purpose'):

  • gsd-phase-researcher — Researches technical approaches for a phase </available_agent_types>

Normalize phase input in step 1 before any directory lookups.

0. Initialize Context

INIT=$(node "/tmp/pomodoro-bench/gsd/.claude/get-shit-done/bin/gsd-tools.cjs" init phase-op "$ARGUMENTS")
if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi

Extract from init JSON: phase_dir, phase_number, phase_name, phase_found, commit_docs, has_research, state_path, requirements_path, context_path, research_path.

Resolve researcher model:

RESEARCHER_MODEL=$(node "/tmp/pomodoro-bench/gsd/.claude/get-shit-done/bin/gsd-tools.cjs" resolve-model gsd-phase-researcher --raw)

1. Validate Phase

PHASE_INFO=$(node "/tmp/pomodoro-bench/gsd/.claude/get-shit-done/bin/gsd-tools.cjs" roadmap get-phase "${phase_number}")

If found is false: Error and exit. If found is true: Extract phase_number, phase_name, goal from JSON.

2. Check Existing Research

ls .planning/phases/${PHASE}-*/RESEARCH.md 2>/dev/null

Read the full file on GitHub · 196 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. yesterday First seen · 196 lines · 25 tokens per session scan A 60cd4356529e

Subscribe to this mod's changes

gsd:research-phase is a command published in the GitHub repository kryptobaseddev/cleo (160 stars, last pushed 15d ago), licensed MIT. It adds 25 tokens to every session and 1,398 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 2026-09-03.