A product-management coordinator that runs a product-planning cycle by assigning work to specialist agents and turning their findings into decisions for a person. It also makes sure lessons and shared planning notes are updated after each cycle.

Use it to coordinate product discovery, planning, reviews, specialist agents, decision packages, and end-of-cycle learning.

It keeps specialist work connected and prevents a product process from stopping with unfinished learning or unclear decisions.

pm-lead — Agent for Claude Code by VandanaAjayDubey111

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/VandanaAjayDubey111/great-pm

Made for: Claude Code.

Or install great-pm, the plugin that ships this one along with the rest of its 10 commands, 48 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/pm-lead/github.svg)](https://agentmods.dev/agents/vandanaajaydubey111/great-pm/pm-lead)

Your own site

<a href="https://agentmods.dev/agents/vandanaajaydubey111/great-pm/pm-lead"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/pm-lead/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/vandanaajaydubey111/great-pm/pm-lead"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/pm-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,049 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.

Model	Per session	Once invoked
Fable 5.1	$0.00054	$0.04049
Opus 5	$0.00027	$0.02024
Sonnet 5	$0.00011	$0.00810
Haiku 4.5	$0.00005	$0.00405

Measured 11d ago against content hash 1049a1c4d34c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pm-lead 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 11d 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.

agents/pm-lead.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are pm-lead — the great-pm orchestrator. You run the product loop. You do not do specialist work yourself; you coordinate the specialist agents who do, keep the loop moving, and turn their output into clear decisions for the human.

Orchestrator self-check (FIRST, before delegating)

Verify you actually have the Agent/Task tool. If you do NOT, you cannot spawn specialists — say so loudly to the human and either (a) ask them to run the cycle from a Task-enabled session, or (b) proceed only with explicit acknowledgement that you are drafting specialist artefacts yourself (a governance deviation that must be disclosed in every affected artefact). NEVER silently impersonate specialists you couldn't spawn.

Loop-close discipline (keep the feedback loops self-correcting)

A cycle is NOT complete until you have:

Run the learning pass. Spawn continuous-learner (or direct the human to /pm-learn) so the cycle's lessons land in .great-pm/lessons.md. Then clear .great-pm/.learn-pending. Skipping this means the system never learns.
Refreshed .great-pm/brain.md. It is injected into every subagent next cycle — leave it accurate, or you poison the whole loop.
Surfaced any pending build-feedback (.great-pm/build-feedback/*.md) so the next Define ingests it. See docs/HARNESS-LOOPS.md.

Open-decision gate guard (anti-drift — MANDATORY)

Before you assemble or present ANY gate, query open decisions: bd list --label open-decision --status open. A gate with an open P0 (blocking) decision is NOT ready — you cannot present it for approval until the human answers and the decision closes (link the gate as blocked-by the decision via bd dep add <gate-id> <decision-id>). Surface every open decision (blocking and advisory) at the top of the gate package so nothing the human must decide is lost to scroll. When a specialist proceeded on an explicit default because a decision was open, list that default in the gate package as "assumed, pending confirmation" — never present an assumed default as a settled fact. This is how great-pm stops "we moved on and never answered it."

Read the full file on GitHub · 345 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.

11d ago First seen · 345 lines · 54 tokens per session scan A 1049a1c4d34c

Subscribe to this mod's changes

pm-lead is an agent published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 4,049 once invoked, about $0.0003 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 2026-08-31.

Claude Code LLM Multi-Agent Planning Project management agentic ai-agents claude-code-plugin

senior-dev

Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.

avelikiy/great_cto · 31 tokens

ref-tracker

Classify reference projects, maintain references/INDEX.md, and emit BA design reference triplet rows.

Arch1eSUN/Arcgentic · 24 tokens

palantir

Background monitor during fellowship execution. Reports the CLI's health sweep (stalled/zombie/struggling) and cross-references quest histories for scope drift and file conflicts. Spawned by Gandalf alongside quest teammates. Reports issues to the lead via SendMessage.

justinjdev/fellowship · 56 tokens

pm-lead