product-manager-contractual

product-manager-contractual is a skill for Claude Code, Codex from SymbolicLight-AGI/contractual-skill. It costs 37 tokens per session (787 once invoked), scanned A, original, MIT.

A planning guide for product managers and teams making product decisions. It organizes goals, users, evidence, assumptions, risks, measurements, and open questions.

In plain words
What is it for?
Use it to shape product opportunities, discovery work, priorities, roadmaps, metrics, trade-offs, and product requirements. It helps turn unclear product input into a plan that can be reviewed.
Why use it?
It prevents teams from treating guesses as facts or making roadmap decisions without enough evidence. It gives different groups a shared basis for reviewing a product choice.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to shape product opportunities, discovery work, priorities, roadmaps, metrics, trade-offs, and product requirements. It helps turn unclear product input into a plan that can be reviewed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/symboliclight-agi/contractual-skill/product-manager
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.

Any agent
npx skills add SymbolicLight-AGI/contractual-skill --skill product-manager
Clone the repo
git clone --depth 1 https://github.com/SymbolicLight-AGI/contractual-skill

Made for: Claude Code, Codex.

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 product-manager-contractual

README.md
[![agentmods](https://agentmods.dev/badge/skills/symboliclight-agi/contractual-skill/product-manager/github.svg)](https://agentmods.dev/skills/symboliclight-agi/contractual-skill/product-manager)
Your own site
<a href="https://agentmods.dev/skills/symboliclight-agi/contractual-skill/product-manager"><img src="https://agentmods.dev/badge/skills/symboliclight-agi/contractual-skill/product-manager/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.

agentmods 80×15 button for product-manager-contractual

Your own site · 80×15
<a href="https://agentmods.dev/skills/symboliclight-agi/contractual-skill/product-manager"><img src="https://agentmods.dev/badge/skills/symboliclight-agi/contractual-skill/product-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 787 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 $0.00037 $0.00787
Opus 5 $0.00018 $0.00394
Sonnet 5 $0.00007 $0.00157
Haiku 4.5 $0.00004 $0.00079

Measured 11d ago against content hash 5623dd2887e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

product-manager-contractual 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.

experiments/market-validated-skills-stage2/skill-variants/contractual/product-manager/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Manager Contract

When To Use

Use this Skill when asked to frame a product opportunity, prioritize work, prepare PRD-style material, define metrics, compare tradeoffs, or turn ambiguous product input into a reviewable plan.

Goal

Produce product guidance that separates goals, users, evidence, assumptions, risks, metrics, and next decisions. The output should help a human product owner choose the next step rather than pretend the product decision is already validated.

Audience

  • Product managers and founders.
  • Engineering, design, data, sales, and customer-facing partners who need a shared product decision artifact.

Inputs

  • Product idea, user segment, customer pain, workflow, current data, known constraints, and requested output format.
  • Optional: usage metrics, customer quotes, roadmap constraints, business goals, competitive notes, support tickets, or prototype feedback.
  • Missing input should be listed as an open question instead of guessed.

Context

Treat supplied task material as the source of truth. Use product frameworks only as structuring aids. Do not invent market data, customer quotes, usage numbers, or roadmap commitments.

Workflow

  1. Restate the product goal and target user.
  2. Extract supplied evidence, assumptions, and constraints.
  3. Identify the decision type: discovery, prioritization, requirements, roadmap, launch, metric review, or risk review.
  4. Build the smallest useful product artifact for that decision.
  5. Make tradeoffs explicit, including what is not being optimized.
  6. Define measurable success criteria and learning loops.
  7. Call out missing evidence and recommend the next validation step.

Permissions

  • May draft product plans, requirement outlines, prioritization matrices, metrics, interview prompts, and risk notes.
  • May not claim customer validation, market sizing, revenue impact, legal approval, engineering feasibility, or executive approval unless the task provides evidence.
  • May not send communications, change a roadmap, create tickets, or commit another team to delivery.

Read the full file on GitHub · 91 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. 11d ago First seen · 91 lines · 37 tokens per session scan A 5623dd2887e5

Subscribe to this mod's changes

product-manager-contractual is a skill published in the GitHub repository SymbolicLight-AGI/contractual-skill (21 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 787 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 2026-08-30.

Related

Other skills, from other repositories