outcome-engineering

outcome-engineering is a skill for Claude Code from sam-dumont/claude-skills. It costs 84 tokens per session (2,181 once invoked), scanned A, original, MIT.

A set of instructions for outcome engineering, an approach that defines the measurable result a software task should achieve before implementation begins. It includes a short framework for stating the intended result and how to verify it.

In plain words
What is it for?
Use it when starting a significant feature, comparing build and purchase options, reframing a failed approach, or defining success and verification for a software task.
Why use it?
It helps prevent work from being judged only by whether code was written. The focus stays on the user-visible change and evidence that it works.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the outcome-engineering plugin — 1 skill shipped together

Good fit Use it when starting a significant feature, comparing build and purchase options, reframing a failed approach, or defining success and verification for a software task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sam-dumont/claude-skills/outcome-engineering
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 sam-dumont/claude-skills --skill outcome-engineering
Clone the repo
git clone --depth 1 https://github.com/sam-dumont/claude-skills

Made for: Claude Code.

Or install outcome-engineering, the plugin that ships this one along with the rest of its 1 skill.

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 outcome-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/sam-dumont/claude-skills/outcome-engineering/github.svg)](https://agentmods.dev/skills/sam-dumont/claude-skills/outcome-engineering)
Your own site
<a href="https://agentmods.dev/skills/sam-dumont/claude-skills/outcome-engineering"><img src="https://agentmods.dev/badge/skills/sam-dumont/claude-skills/outcome-engineering/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 outcome-engineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/sam-dumont/claude-skills/outcome-engineering"><img src="https://agentmods.dev/badge/skills/sam-dumont/claude-skills/outcome-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,181 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 $0.00084 $0.02181
Opus 5 $0.00042 $0.01091
Sonnet 5 $0.00017 $0.00436
Haiku 4.5 $0.00008 $0.00218

Measured 10d ago against content hash 89af7c2a62e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

outcome-engineering 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 10d 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.

plugins/outcome-engineering/skills/outcome-engineering/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Outcome Engineering (o16g)

Based on the o16g manifesto by Cory Ondrejka. Software engineering is outcome delivery, not code production.

Task Thinking Outcome Thinking
"Build feature X" "Enable users to achieve Y, verified by Z"
"Fix bug B" "Restore correct behavior, prevent recurrence"
"Refactor module M" "Reduce change cost from X to Y, measured by Z"
"Add technology T" "Solve problem P with measurable improvement"

Phase 1: The Outcome Frame

Before starting significant work, produce an Outcome Frame. This takes ~3 minutes, not 30. Skip it for trivial tasks (typo fixes, obvious single-line bugs).

1. Define the Outcome (P01: Human Intent)

State the measurable change being delivered. Not what you'll build — what will be different when you're done.

Anti-pattern: "Build a REST API for user management" Outcome-first: "External services can create, read, update, and delete user records over HTTP, with <200ms p95 latency"

Ask: "What is measurably different when this is done?"

2. Define Verification (P02: Verified Reality)

How will you PROVE it worked? Not "it looks right" — observable, repeatable evidence.

Verification must be concrete:

  • Tests that pass/fail (unit, integration, e2e)
  • Observable behavior (API returns X, UI shows Y)
  • Metrics that move (latency drops, error rate decreases)
  • User action that succeeds (can complete workflow Z)

Anti-pattern: "Test it manually and make sure it works" Outcome-first: "Integration test hits /users CRUD endpoints, asserts 2xx responses and correct payloads. Load test confirms p95 <200ms at 100 RPS."

Ask: "What specific evidence proves this outcome was achieved?"

3. Justify the Cost (P04: Backlog Dead)

Is this worth the compute/effort? Not everything that could be built should be built.

Consider:

  • Does this directly serve a user need or business goal?
  • What's the cost of NOT doing this?
  • Is there a simpler way to achieve 80% of the outcome?
  • Are we building or should we buy/integrate?

Read the full file on GitHub · 235 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. 10d ago First seen · 235 lines · 84 tokens per session scan A 89af7c2a62e9

Subscribe to this mod's changes

outcome-engineering is a skill published in the GitHub repository sam-dumont/claude-skills (39 stars, last pushed 6mo ago), licensed MIT. It adds 84 tokens to every session and 2,181 once invoked, about $0.0004 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens