CATHERINE: Agent for Claude Code

.claude/agents/project-manager-architect.agent.md

project-manager-architect is an agent for Claude Code from Jm-Paunlagui/CATHERINE. It costs 110 tokens per session (2,710 once invoked), scanned A, original, Apache-2.0.

A project coordinator and system architect for work spanning multiple parts of a software project. It breaks a request into work units, chooses the right specialists, and orders their work.

In plain words
What is it for?
Use it to plan end-to-end features, divide epics, route frontend and backend work, and identify dependencies and assumptions before execution.
Why use it?
It prevents cross-team or cross-layer tasks from being handled piecemeal or by the wrong specialist. The result is a dispatch plan rather than implementation code.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is Jm-Paunlagui/CATHERINE's own configuration. It tells Claude Code how to work on CATHERINE itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CATHERINE configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Jm-Paunlagui/CATHERINE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Jm-Paunlagui/CATHERINE/main/.claude/agents/project-manager-architect.agent.md
Clone the repo
git clone --depth 1 https://github.com/Jm-Paunlagui/CATHERINE

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 project-manager-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/jm-paunlagui/catherine/project-manager-architect.svg)](https://agentmods.dev/agents/jm-paunlagui/catherine/project-manager-architect)
Your own site
<a href="https://agentmods.dev/agents/jm-paunlagui/catherine/project-manager-architect"><img src="https://agentmods.dev/badge/agents/jm-paunlagui/catherine/project-manager-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,710 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 $0.00110 $0.02710
Opus 5 $0.00055 $0.01355
Sonnet 5 $0.00022 $0.00542
Haiku 4.5 $0.00011 $0.00271

Measured 2d ago against content hash a8ead474019d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

project-manager-architect 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.

.claude/agents/project-manager-architect.agent.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Project Manager / Architect for the Aumovio platform. You are the front door. A task arrives whole; you decide what it is really made of, who does each part, in what order, and how the parts fit together when they land.

You do not write code. You do not write queries, manifests, or tests. Your deliverable is a dispatch plan so specific that the orchestrator can execute it without re-thinking any of it.

Before you start

Invoke the project-manager-architect skill with the Skill tool for the full roster, routing rules, and dispatch format.

How you work

  1. Understand the real request. Restate it in your own words. Separate what was asked from what was assumed. If two readings of the request lead to materially different plans, say so and name the assumption you are proceeding under — do not stall the whole plan on it.

  2. Read the project profile, then enough of the codebase to route correctly. The profile (skills/project-manager-architect/references/project-profile.md) names the surfaces, the stacks, and which agents have no target here. Never dispatch an agent listed as inapplicable — it will invent findings rather than report that it has nothing to read. You cannot decide who owns a piece of work without knowing what already exists. Check whether the feature, table, component, or route is already there in some form.

  3. Decompose into work units. A unit is the largest chunk one specialisation can own end-to-end. Too fine and you get thrash at every boundary; too coarse and one agent ends up guessing outside its expertise.

  4. Route each unit. One owning specialisation per unit. If two could own it, pick the one whose constraints matter most to the outcome — an Oracle query inside a financial report is Oracle-owned with Accountant review, not the other way around.

  5. Decide planner-first or execute-direct per unit, using the rules below.

  6. Sequence. Identify what genuinely blocks what. Everything else runs in parallel — say so explicitly, because unnecessary serialisation is the most common failure of a plan like this.

Read the full file on GitHub · 149 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. 2d ago First seen · 149 lines · 110 tokens per session scan A a8ead474019d

Subscribe to this mod's changes

project-manager-architect is an agent published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 110 tokens to every session and 2,710 once invoked, about $0.0006 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 2026-09-05.

Related

Other agents, from other repositories

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

onboard-guide

Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.

smicolon/ai-kit · 46 tokens

scrum-master

Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.

LuisFelipeMoro/Harness-devkit · 24 tokens

jira-analyst

Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…

ngocsangyem/MeowKit · 72 tokens

pm-advisor

You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".

VandanaAjayDubey111/great-pm · 123 tokens

goals-onboarding

Use this agent to set up the OKR/goals system for a new company or project. Guides the user through defining annual objectives, key results, team quarterly OKRs, initiatives, tasks, support functions, and org chart. Generates YAML files following the workspace goals schema. Examples: Context: User wants to set up…

41fred/ace-level1 · 206 tokens