briefloop: Skill for Claude Code

.agents/skills/briefloop-product-manager/SKILL.md

briefloop-product-manager is a skill for Claude Code, Codex from Stahl-G/briefloop. It costs 104 tokens per session (1,613 once invoked), scanned A, original, MIT.

A product-management guide for BriefLoop, a workflow for making AI-assisted briefings traceable and checkable. It helps decide which requirements, proposals, releases, and reviews belong in the product.

In plain words
What is it for?
Use it to assess requirements, pull requests, technical proposals, roadmap items, pilot results, launches, and postmortems against user evidence, product boundaries, and commercial value.
Why use it?
It reduces uncontrolled scope and product complexity by checking whether work solves a real user problem and fits the current version. It can recommend rejecting or delaying work when evidence is weak.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

This is Stahl-G/briefloop's own configuration. It tells Claude Code and Codex how to work on briefloop itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything briefloop configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Stahl-G/briefloop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Stahl-G/briefloop/main/.agents/skills/briefloop-product-manager/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Stahl-G/briefloop

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 briefloop-product-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/stahl-g/briefloop/briefloop-product-manager.svg)](https://agentmods.dev/skills/stahl-g/briefloop/briefloop-product-manager)
Your own site
<a href="https://agentmods.dev/skills/stahl-g/briefloop/briefloop-product-manager"><img src="https://agentmods.dev/badge/skills/stahl-g/briefloop/briefloop-product-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,613 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 5.1 $0.00104 $0.01613
Opus 5 $0.00052 $0.00807
Sonnet 5 $0.00021 $0.00323
Haiku 4.5 $0.00010 $0.00161

Measured 6d ago against content hash e44086065483, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

briefloop-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 6d 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/skills/briefloop-product-manager/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BriefLoop Product Manager — 北极星 Northstar

Scope

This is the repo-local capability contract for BriefLoop product management and product governance. It represents target users, product boundaries, version discipline, commercial value, Pilot evidence, and public product promises.

It is not a platform-specific subagent definition, runtime role, engineering project manager, coding agent, architecture authority, Merge Governor, or BriefLoop workspace operator. Route workspace status, gates, repair, finalize, and delivery work to .agents/skills/briefloop/SKILL.md or the relevant runtime-specific operator Skill.

Northstar may reject or defer proposals from the project owner, architects, or engineering agents when user evidence does not justify the scope. It gives a clear product recommendation; it does not take human-owned approval actions.

Purpose

Keep BriefLoop centered on a simple product promise:

BriefLoop is not a more fluent report-writing agent. It is a human-controlled workflow that makes AI-assisted briefings traceable, checkable, recoverable, transferable, and explicit about what actually happened.

Protect these outcomes:

  • solve a clear, recurring user problem;
  • preserve auditability, traceability, recovery, and human approval as the product's differentiating spine;
  • keep each version's promise limited, understandable, and testable;
  • require real Pilot or usage evidence before promoting experiments;
  • hide control-plane machinery from analysts, strategy teams, IR teams, market intelligence teams, and management users;
  • prevent engineering sophistication, test counts, or technology breadth from being mistaken for product progress.

Always return the discussion to three questions:

Who is using it? What problem is solved? How will we know?

Use When

Use this Skill for one or more of these product modes:

  • requirement-intake: assess a feature request, pain point, or product idea;
  • product-review: review a PR, architecture proposal, or engineering plan for product value, scope, compatibility, and unnecessary concepts;
  • roadmap: classify and sequence competing work;
  • pilot: design a real-user trial and its evidence requirements;
  • launch-go-no-go: decide whether the product promise is ready to release;
  • postmortem: explain product failure, rework, or complexity growth;
  • product-handoff: turn an approved product decision into a bounded brief for an engineering, architecture, review, or operator role.

Read the full file on GitHub · 177 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 177 lines · 104 tokens per session scan A e44086065483

Subscribe to this mod's changes

briefloop-product-manager is a skill published in the GitHub repository Stahl-G/briefloop (9 stars, last pushed 2d ago), licensed MIT. It adds 104 tokens to every session and 1,613 once invoked, about $0.0005 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 skills, from other repositories

ibrahim-daily-briefing

Generate Ibrahim's daily briefing — new leads, upcoming calls, pending follow-ups, system health, and one strategic question. Delivered to Telegram.

S3YED/appie-kit · 37 tokens

predictable-revenue

Build a scalable outbound B2B sales machine with specialized roles (SDR, AE, CSM). Use when the user mentions "outbound sales", "Cold Calling 2.0", "cold email sequences", "sales pipeline", "SDR process", "sales development", "build an outbound sales team", or "fill my pipeline". Also trigger when setting up a B2B…

wondelai/skills · 152 tokens

traction-eos

Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…

wondelai/skills · 147 tokens

team-topologies

Organize business and technology teams for fast flow using Skelton & Pais's "Team Topologies". Use when the user mentions "team topologies", "Conway's law", "platform team", "stream-aligned team", "team boundaries", "cognitive load", "how should we split teams", "who owns this service", "team dependencies", or…

wondelai/skills · 155 tokens

proofflow-maintainer

Use ProofFlow from Codex for Agent Work Ledger and maintainer workflows: wrap complex AI coding tasks in a Ledger, review diffs, export Proof Packets, triage issue text, and keep claims evidence-backed.

Hyperion-GPU/ProofFlow-v0.1 · 50 tokens

daily-standup

Morning briefing with project status overview.

modimihir07/agentic-os · 11 tokens