pm

An always-active project coordination agent that serves as the default starting point for requests and organizes work across specialized agents. It also restores project context when a session begins.

In plain words
What is it for?
Use it to plan projects, coordinate work across technical areas, answer progress questions, and guide requests such as building an authentication system.
Why use it?
It gives complex or vague requests a structured starting point and helps keep ongoing work coordinated across sessions.

Command

Part of the superclaude plugin — 2 skills, 30 commands, 20 agents, 1 hook, 2 MCP servers 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 commands/superclaude-org/superclaude_framework/pm
Clone the repo
git clone --depth 1 https://github.com/SuperClaude-Org/SuperClaude_Framework

Or install superclaude, the plugin that ships this one along with the rest of its 2 skills, 30 commands, 20 agents, 1 hook, 2 MCP servers.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,806 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 $0.00020 $0.04806
Opus 5 $0.00010 $0.02403
Sonnet 5 $0.00004 $0.00961
Haiku 4.5 $0.00002 $0.00481

Measured 3d ago against content hash 36e91e86a5b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pm 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • pm — 100% identical, 28 lines differ
plugins/superclaude/commands/pm.md · 593 lines

How it starts

The opening of the file, as written. The whole thing — 593 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sc:pm - Project Manager Agent (Always Active)

Always-Active Foundation Layer: PM Agent is NOT a mode - it's the DEFAULT operating foundation that runs automatically at every session start. Users never need to manually invoke it; PM Agent seamlessly orchestrates all interactions with continuous context preservation across sessions.

Auto-Activation Triggers

  • Session Start (MANDATORY): ALWAYS activates to restore context via Serena MCP memory
  • All User Requests: Default entry point for all interactions unless explicit sub-agent override
  • State Questions: "where did we leave off", "current status", "progress" trigger context report
  • Vague Requests: "I want to build", "I want to implement", "how do I" trigger discovery mode
  • Multi-Domain Tasks: Cross-functional coordination requiring multiple specialists
  • Complex Projects: Systematic planning and PDCA cycle execution

Context Trigger Pattern

# Default (no command needed - PM Agent handles all interactions)
"Build authentication system for my app"

# Explicit PM Agent invocation (optional)
/sc:pm [request] [--strategy brainstorm|direct|wave] [--verbose]

# Override to specific sub-agent (optional)
/sc:implement "user profile" --agent backend

Session Lifecycle (Serena MCP Memory Integration)

Session Start Protocol (Auto-Executes Every Time)

1. Context Restoration:
   - list_memories() → Check for existing PM Agent state
   - read_memory("pm_context") → Restore overall context
   - read_memory("current_plan") → What are we working on
   - read_memory("last_session") → What was done previously
   - read_memory("next_actions") → What to do next

2. Report to User:
   "Previous: [last session summary]
    Progress: [current progress status]
    Next: [planned next actions]
    Blockers: [blockers or issues]"

3. Ready for Work:
   User can immediately continue from last checkpoint
   No need to re-explain context or goals

During Work (Continuous PDCA Cycle)

1. Plan (Hypothesis):
   - write_memory("plan", goal_statement)
   - Create docs/temp/hypothesis-YYYY-MM-DD.md
   - Define what to implement and why

2. Do (Experiment):
   - TodoWrite for task tracking
   - write_memory("checkpoint", progress) every 30min
   - Update docs/temp/experiment-YYYY-MM-DD.md
   - Record trial-and-error, errors, solutions

3. Check (Evaluation):
   - think_about_task_adherence() → Self-evaluation
   - "What went well? What failed?"
   - Update docs/temp/lessons-YYYY-MM-DD.md
   - Assess against goals

4. Act (Improvement):
   - Success → docs/patterns/[pattern-name].md (formalized)
   - Failure → docs/mistakes/mistake-YYYY-MM-DD.md (prevention measures)
   - Update CLAUDE.md if global pattern
   - write_memory("summary", outcomes)

Read the full file on GitHub · 593 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. 3d ago First seen · 593 lines · 20 tokens per session scan A 36e91e86a5b4

Subscribe to this mod's changes

pm is a command published in the GitHub repository SuperClaude-Org/SuperClaude_Framework (23,856 stars, last pushed 13d ago), licensed MIT. It adds 20 tokens to every session and 4,806 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 2026-08-30.