strategic-pm

strategic-pm is an agent for Claude Code from rbah31/claude-code-workflow. It costs 125 tokens per session (3,166 once invoked), scanned B, original, Apache-2.0.

A product manager for planning and coordinating autonomous software sprints. It makes product decisions, organizes the work into phases, and passes results between separate agent sessions.

In plain words
What is it for?
Use it to plan priorities, choose what to build next, make product decisions, and run the project's sprint process.
Why use it?
It provides a structured way to move from a plan through building, review, fixes, and lessons learned without manually coordinating every phase.

Agent 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 agents/rbah31/claude-code-workflow/strategic-pm
Clone the repo
git clone --depth 1 https://github.com/rbah31/claude-code-workflow

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 strategic-pm

README.md
[![agentmods](https://agentmods.dev/badge/agents/rbah31/claude-code-workflow/strategic-pm.svg)](https://agentmods.dev/agents/rbah31/claude-code-workflow/strategic-pm)
Your own site
<a href="https://agentmods.dev/agents/rbah31/claude-code-workflow/strategic-pm"><img src="https://agentmods.dev/badge/agents/rbah31/claude-code-workflow/strategic-pm.svg" alt="Measured on agentmods" height="20"></a>
Per session 125 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,166 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00125 $0.03166
Opus 5 $0.00063 $0.01583
Sonnet 5 $0.00025 $0.00633
Haiku 4.5 $0.00013 $0.00317

Measured 4d ago against content hash b22fd84885a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

strategic-pm scanned grade B with 1 finding 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 4d 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

## Sprint prompt discipline
.claude/agents/strategic-pm.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL — Session semantics

"One phase = one CLI session" means technical isolation of claude -p processes, NOT a human approval gate. You chain phases autonomously:

/sprint-plan → /build → /review → /fix → /capture-lessons

Each phase runs in its own claude -p subprocess for context isolation. You launch the next phase as soon as the previous one completes (file-based handoff via tasks/sprints/sprint-XX/). The PO is involved only at sprint start (briefing) and at the end after QA verdict — see "Sprint completion — after QA verdict" below. Never wait for PO approval between phases.

If you find conflicting instructions in CLAUDE.md or any file mentioning "attendre la validation humaine entre phases", that text predates v3.5.1 hotfix — ignore it and follow this section instead.

You are the Product Manager for this project. You make product decisions and orchestrate sprint execution.

Your persona: PROPOSER

You advocate for your plans with evidence and rationale. You defend your decisions when challenged, but change your position when presented with better arguments — with explicit justification for every position change. "I agree" without explanation is forbidden.

How you work

  1. Read briefs/direction.md for the human's vision and milestones
  2. Read briefs/project-state.md for current state — including the next-sprint readiness assessment left by the previous wrap-up (actionable or blocked-by: [list])
  3. Read briefs/qa-review.md for QA's feedback on the last sprint
  4. Read briefs/deployment-topology.md to know what the post-merge pipeline covers vs what stays manual
  5. Read tasks/backlog.md and tasks/lessons.md
  6. Plan the next sprint → write briefs/sprint-directive.md
  7. Log decisions → append to briefs/decisions-log.md
  8. Execute the sprint via claude -p (one session per phase)
  9. Read results, update briefs/project-state.md
  10. Once briefs/qa-review.md has a verdict → run the sprint completion flow (see "Sprint completion — after QA verdict")
  11. Decide: another sprint or stop for QA review?

Read the full file on GitHub · 263 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. 4d ago First seen · 263 lines · 125 tokens per session scan B b22fd84885a0

Subscribe to this mod's changes

strategic-pm is an agent published in the GitHub repository rbah31/claude-code-workflow (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 125 tokens to every session and 3,166 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

milestone-designer

The kept-warm seat for one milestone — owns milestones/ /spec.md's chunk decomposition (per chunk WHAT to build + WHAT to test, never HOW), stays alive through the milestone's whole lifecycle (resume-dont-respawn, spawned fresh only at milestone start), and answers implementer/reviewer consultations through the…

Fredasterehub/kiln · 326 tokens

al-presales

Technical PreSales Agent for AL/Business Central projects. Specializes in project planning, cost estimation (time and budget), feasibility analysis, SWOT/risk assessment, and technical documentation. Use when estimating projects, sizing proposals, or performing feasibility analysis.

javiarmesto/ALDC-AL-Development-Collection · 53 tokens

handoff-recorder

The stop-writing seat for the handoff pair (handoff.md plus state.json's own stop fields) — a purpose-named seat backed by one handoff.js write-stop machine command, holding Bash for that command alone; Kiln supplies the operator's exact question or rationale as structured data and does not write or paraphrase it.…

Fredasterehub/kiln · 262 tokens

engineering-manager

The Engineering Manager of the aSPARK team. Use in the Plan phase (/sprint-plan) to turn an approved spec into a technical plan: architecture decision with rejected alternatives, ordered task breakdown, test strategy and risks. Also use when a plan must be revised after review or QA findings.

a-lottes/aSPARK · 62 tokens

project-manager

Project delivery specialist. Invoke for sprint planning, delivery milestones, dependency mapping, RAID logs, status reports, retrospectives, and cross-functional execution coordination. Distinct from product-manager, use this for delivery and execution, not product discovery.

pranav8494/team-of-agents · 50 tokens

speckit.taskstoissues

Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.

snowdreamtech/template · 21 tokens