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 evanmcgoogan/skin-in-the-game --skill delete-the-requirementgit clone --depth 1 https://github.com/evanmcgoogan/skin-in-the-gameWrote 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/evanmcgoogan/skin-in-the-game/delete-the-requirement)<a href="https://agentmods.dev/skills/evanmcgoogan/skin-in-the-game/delete-the-requirement"><img src="https://agentmods.dev/badge/skills/evanmcgoogan/skin-in-the-game/delete-the-requirement/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/evanmcgoogan/skin-in-the-game/delete-the-requirement"><img src="https://agentmods.dev/badge/skills/evanmcgoogan/skin-in-the-game/delete-the-requirement.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 | $0.00112 | $0.00492 |
| Opus 5 | $0.00056 | $0.00246 |
| Sonnet 5 | $0.00022 | $0.00098 |
| Haiku 4.5 | $0.00011 | $0.00049 |
Grade A, and why
delete-the-requirement 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 12d 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.
What it actually says
Delete the Requirement
The most common and most expensive engineering error is building, measuring, or optimizing something that should not exist. Optimization makes a thing faster; deletion makes it free. So before you build or improve anything, try to delete the requirement first. (Principle 7.)
The order of operations (do NOT reorder)
Borrowed from the discipline of people who build hard things:
- Question every requirement. For each one, ask who it came from — a named person, never "the system" or "best practice" — and why. A requirement that can't name its owner or its reason is the first to cut.
- Delete it. Try to remove the requirement, the part, the step, the metric, the abstraction. If you're never forced to add something back, you didn't delete enough.
- Simplify what survives.
- Only then optimize. Optimizing before deleting is polishing something that belongs in the bin.
What to challenge
- Features nobody asked for but that "seem expected"
- Config options, flags, and abstractions added "for flexibility" before there are two real cases
- Metrics that don't change a decision — a number nobody acts on is noise dressed as rigor
- Build steps and dependencies kept out of habit
How to surface a deletion
Deleting a requirement the human explicitly stated can be a CEO-line call — if so, raise it as a quick recommendation with the cost it saves; don't silently drop it. If it's clearly below the line — an internal abstraction, a redundant step — just delete it and note it in passing.
The test
The best part is no part. The best feature is no feature. The best metric is no metric. If deleting it costs less than keeping it, delete it.
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.
- 12d ago First seen · 29 lines · 112 tokens per session scan A 219b076ae3bd
delete-the-requirement is a skill published in the GitHub repository evanmcgoogan/skin-in-the-game (1 stars, last pushed 3mo ago), licensed MIT. It adds 112 tokens to every session and 492 once invoked, about $0.0006 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
codex
Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.
commit
A guided process for committing code changes to Git. It checks the working tree, follows a conventional commit format, links a task when available, reviews the changes, and asks for approval.
orient
Internal skill for commands. Render the shared orientation snapshot - active task, what's in flight, what's next - tracker-universal. Do not trigger on user conversation; only when a command needs the snapshot.
design
Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…
x-cr
A software-correctness investigation skill for finding why code behaves differently from what was expected. It uses evidence from code paths, specifications, tests, logs, and changes to assess possible causes.
x-multi-llm-align
A review process in which two sub-agents examine an API, data format, event schema, or workflow from their separate implementation perspectives. The user passes documents and feedback between them over multiple rounds.