project-manager

project-manager is an agent for Claude Code from HirogaKatageri/hirokata. It costs 75 tokens per session (4,640 once invoked), scanned A, original, MIT.

A requirements-gathering agent that interviews a user and produces a clear requirements document for an implementation team. It works through an orchestrator, which passes questions to and answers from the user.

In plain words
What is it for?
It helps clarify a new project request, record the answers as requirements, and collaborate with an architecture planner on the resulting work.
Why use it?
It prevents implementation plans from being based on guessed requirements or missing decisions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

Part of the guild plugin — 20 skills, 15 agents shipped together

Good fit It helps clarify a new project request, record the answers as requirements, and collaborate with an architecture planner on the resulting work.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hirogakatageri/hirokata/project-manager
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.

Clone the repo
git clone --depth 1 https://github.com/HirogaKatageri/hirokata

Made for: Claude Code.

Or install guild, the plugin that ships this one along with the rest of its 20 skills, 15 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 project-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/hirogakatageri/hirokata/project-manager/github.svg)](https://agentmods.dev/agents/hirogakatageri/hirokata/project-manager)
Your own site
<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/project-manager"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/project-manager/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for project-manager

Your own site · 80×15
<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/project-manager"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/project-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,640 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00075 $0.04640
Opus 5.5 $0.00030 $0.01856
Sonnet 5.5 $0.00015 $0.00928
Haiku 4.5 $0.00007 $0.00464

Measured 25d ago against content hash 63a3b78c05c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project-manager 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 25d 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/guild/agents/project-manager.md · 376 lines

How it starts

The opening of the file, as written. The whole thing — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Manager — Guild Agent

You are the Guild's Project Manager. Your job is to gather requirements from the user through focused conversation, then produce a clear, comprehensive requirement document that the strategist can turn into an implementation plan.

You cannot talk to the user directly. You are a subagent — AskUserQuestion only works in the main session, not here, even if it were listed in your tools. Every round of questions goes through the orchestrator via a relay protocol (below): you propose questions, end your turn, the orchestrator asks the real user and resumes you with the answers. Never attempt to ask the user directly or invent an answer on the user's behalf — always relay.

How You're Spawned

You are spawned directly by the new-requirement skill, not via a board ticket — there is no ticket to read, and you run alone: the strategist does not start until you report done. Your dispatch prompt gives you:

  • The working title, and whatever description the user has already given
  • The REQ ID if one already exists (a resumed session); on a fresh run there is none yet — you create the requirement at the end, once the document is written

The Warehouse — How You Read and Write the Board

Load the guild:warehouse skill before your first query — it carries the seven rules (hex transport, PRAGMA foreign_keys, RETURNING discipline, never parsing free text on |, errors on stdout, and the rest) that apply to every statement below. Take every query from its references/queries.md — in particular the id-derivation pattern in §1, which is how a REQ gets its number without a read-then-write race.

export PATH="$HOME/.turso:$PATH"
DB=.guild/guild.db          # cloud boards: see the skill's Connect section

One addition specific to your documents: encode a whole requirement body from a file, never a variable — hex=$(xxd -p < req.md | tr -d '\n'), then CAST(x'$hex' AS TEXT) — so the content never passes through the shell and no trailing newline is eaten.

Read the full file on GitHub · 376 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. 25d ago Changed · -73 lines · -4 tokens per session 63a3b78c05c4
  2. 1mo ago First seen · 449 lines · 79 tokens per session scan A 995676baf357

Subscribe to this mod's changes

project-manager is an agent published in the GitHub repository HirogaKatageri/hirokata (6 stars, last pushed 9d ago), licensed MIT. It adds 75 tokens to every session and 4,640 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-09.

Related

Other agents, from other repositories