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.
npx skills add EzraApple/skills-init --skill outcome-first-workflowsgit clone --depth 1 https://github.com/EzraApple/skills-initWrote 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.
[](https://agentmods.dev/skills/ezraapple/skills-init/outcome-first-workflows)<a href="https://agentmods.dev/skills/ezraapple/skills-init/outcome-first-workflows"><img src="https://agentmods.dev/badge/skills/ezraapple/skills-init/outcome-first-workflows/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.
<a href="https://agentmods.dev/skills/ezraapple/skills-init/outcome-first-workflows"><img src="https://agentmods.dev/badge/skills/ezraapple/skills-init/outcome-first-workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.00819 |
| Opus 5 | $0.00029 | $0.00409 |
| Sonnet 5 | $0.00012 | $0.00164 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
outcome-first-workflows 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outcome-First Workflows
Run substantial work against a visible finish line. Define what must become true, which constraints matter, and what evidence will prove completion; leave routine implementation choices open.
Route Nearby Work
- Use
plan-changeswhen the requested deliverable is an implementation plan. - Use
systematic-debuggingwhen the cause of broken behavior is unknown. - Use
adversarial-reviewwhen the user explicitly wants independent, high-scrutiny review. - Handle small, directly verifiable tasks without adding workflow ceremony.
Establish the Contract
Before substantive work, derive a compact contract from the request and local context:
Outcome: <observable end state>
Constraints: <scope, safety, compatibility, authority>
Non-goals: <adjacent work intentionally excluded>
Done when:
- <claim> -> <evidence that can prove it>
Stop or ask when: <human decision or authority boundary>
Do not turn this into a screenplay. Include decisions that control the result, not a command-by-command itinerary.
Ask the user only about choices that cannot be discovered and would materially change the result. Resolve codebase facts, tool availability, and current state directly when safe.
Match Evidence to the Claim
Choose the witness before implementing when verification affects the design.
| Completion claim | Appropriate witness |
|---|---|
| A user flow works | Exercise the real UI or equivalent user surface. |
| Hidden state changed | Read it back through the owning API, CLI, log, or datastore. |
| A code contract holds | Run the narrow test, type check, lint, or contract probe that exercises it. |
| Performance improved | Compare repeated baseline and treatment runs under the same load. |
| A deployment shipped | Verify the deployment job and the served artifact or live behavior. |
| An external artifact changed | Re-open the external artifact; a local diff cannot prove it. |
One witness may support several claims, but a convenient witness must not stand in for the relevant one. A build does not prove a user interaction, and a UI check does not prove a database invariant.
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.
- 9d ago First seen · 96 lines · 58 tokens per session scan A 6e3386fa3ec0
outcome-first-workflows is a skill published in the GitHub repository EzraApple/skills-init (2 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 819 once invoked, about $0.0003 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.
Other skills, from other repositories
help-flow
Help about Rosetta: explains capabilities and usage.
external-lib-flow
Workflow for onboarding an external private library so AI can use it without source access.
modernization-flow
Workflow for converting, modernizing, upgrading, or re-architecting code (e.g. C++→Java, monolith→microservices), etc.
coding-flow
Light coding workflow: features, fixes, refactors, unit tests, etc.; scales small to large.
adhoc-flow
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
coding-agents-prompting-flow
Workflow for authoring and adapting AI-agent prompts: skills, agents, workflows, rules, etc.