product-manager

product-manager is an agent for Claude Code from Pierry/harness-kit. It costs 35 tokens per session (276 once invoked), scanned A, original, MIT.

A product-management coordinator that runs the process from an initial intake through a PRD and an engineering handoff prompt.

In plain words
What is it for?
Use it to coordinate intake, requirements writing, and engineering handoff for a proposed feature.
Why use it?
It connects the product-planning stages so later work can use gathered project context instead of repeatedly asking for it.

Agent for Claude Code

Part of the harness-kit plugin — 14 skills, 17 commands, 4 agents, 4 hooks 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 agents/pierry/harness-kit/product-manager
Clone the repo
git clone --depth 1 https://github.com/Pierry/harness-kit

Made for: Claude Code.

Or install harness-kit, the plugin that ships this one along with the rest of its 14 skills, 17 commands, 4 agents, 4 hooks.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 276 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 $0.00035 $0.00276
Opus 5 $0.00017 $0.00138
Sonnet 5 $0.00007 $0.00055
Haiku 4.5 $0.00003 $0.00028

Measured 3d ago against content hash 814a59533e69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

product-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 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.

.claude/agents/product-manager.md · 21 lines

What it actually says

Product Manager.

When invoked, run /product-manager:run end to end. Follow .claude/agents/product-manager/guides/pipeline.md.

Inputs come from intake, not the human. If .claude/runtime/outputs/intake/{feature_id}.md is missing, run /intake:run first, then read it. Take squad, problem, customers, hypothesis, and metric from intake; carry its NEEDS REVIEW markers forward unchanged (resolve-mark-proceed). Never stop to ask for an input intake could harvest.

Operating rules:

  • English by default. Domain terms stay native if team uses them.
  • Never invent. Mark gaps with NOT FOUND - NEEDS REVIEW: {detail}.
  • Voice: read .claude/agents/product-manager/guides/writing-style.md. No em-dashes. Mermaid not ASCII.
  • Specific over generic. Real numbers, names, quotes.

Return format: see .claude/commands/product-manager/run.md. Include paths, scores, attempts, publish status, blockers.

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 · 21 lines · 35 tokens per session scan A 814a59533e69

Subscribe to this mod's changes

product-manager is an agent published in the GitHub repository Pierry/harness-kit (3 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 276 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

tool-hub

Первая встроенная поверхность Tool Hub: восемь типизированных video. контрактов, локальный staging, provenance, pinned CLI и deny-by-default исполнение.

romarayt/raytsystem-public-os · 34 tokens

creating-extensions

Как устроены skill (skills//SKILL.md), определение агента (packs//agents/.yaml) и pack. Правила безопасности расширений: инертность, разрешённые корни, отсутствие произвольного shell и невозможность самоназначить доверие.

romarayt/raytsystem-public-os · 58 tokens

overview

Как устроен каталог расширений raytsystem: агенты, навыки, контексты, packs, манифесты, происхождение и доверие. Каталог собирается только из фиксированных разрешённых корней, а манифест не может сам объявить себя официальным.

romarayt/raytsystem-public-os · 61 tokens

packs-lifecycle

Как raytsystem принимает pack: discover, inspect, validate, approve, install, activate, update и rollback. Карантин на входе, проверка хешей на каждом переходе, обязательный approval и прохождение eval.

romarayt/raytsystem-public-os · 48 tokens

ap-preflight-probe

L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.

Spielewoy/autoprompt-skill · 39 tokens

task-plan-architect

Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.

MercurieVV/ScalaSemantic · 47 tokens