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 vinta/hal-9000 --skill fuck-over-engineeringgit clone --depth 1 https://github.com/vinta/hal-9000Wrote 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/vinta/hal-9000/fuck-over-engineering)<a href="https://agentmods.dev/skills/vinta/hal-9000/fuck-over-engineering"><img src="https://agentmods.dev/badge/skills/vinta/hal-9000/fuck-over-engineering.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00085 | $0.00798 |
| Opus 5 | $0.00043 | $0.00399 |
| Sonnet 5 | $0.00017 | $0.00160 |
| Haiku 4.5 | $0.00009 | $0.00080 |
Grade A, and why
fuck-over-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 2d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fuck Over-Engineering
Audit the scope for over-engineering and report what to cut, ranked biggest cut first. The best outcome is a shorter codebase with the same behavior. The argument is the scope; without one, the whole tree. Read what the scope holds before judging it, and fan out subagents when it will not fit in context.
Tags
delete:dead code, unused flexibility, speculative feature. Nothing replaces it.reuse:bespoke code that a helper already in this codebase, or an installed dependency, already provides. Name the helper or function.stdlib:hand-rolled thing the language's standard library ships. Name the function.native:dependency or code doing what the platform already does. Name the feature.yagni:abstraction with one implementation, config nobody sets, layer with one caller.shrink:same logic, fewer lines. Show the shorter form.
Hunt
Dependencies the stdlib or platform already covers, single-implementation interfaces, factories with one product, wrappers that only delegate, files exporting one thing, dead flags and config, hand-rolled stdlib, near-duplicates of an existing helper, special-case branches bolted onto shared paths, feature logic living in shared modules.
Evidence
Every finding cites the evidence that makes it a cut: caller count, implementation count, or the stdlib or platform feature and the version that ships it. Count callers through dynamic dispatch, entry points, hooks, and tests, not grep alone. A published package's public export stays at zero in-repo callers. Verify stdlib: and native: claims against current docs (the find-docs skill when present) before asserting them.
A finding removes lines or concepts; moving them between files is a refactor, not a cut. Fewer, bigger cuts beat a long list: a shrink: that saves two lines earns a slot only when it also removes a concept.
Output
One line per finding, numbered, ranked biggest cut first:
N. <tag> <what to cut>. <replacement>. <evidence>. [path:line]
What ships with it
1 file 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.
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.
- 2d ago Changed · -7 tokens per session 7abf1e7d3058
- 8d ago First seen · 48 lines · 92 tokens per session scan A 5dbf05976d4b
fuck-over-engineering is a skill published in the GitHub repository vinta/hal-9000 (128 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 798 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.
Other skills, from other repositories
code-quality
Comprehensive code review for Java - clean code principles, API contracts, null safety, exception handling, and performance. Use when user says "review code", "refactor", "check API", or before merging changes.
knowledge-audit
Review and clean up stored memories — find duplicates, contradictions, stale entries, and consolidate.
devops-infra
DevOps & Infrastructure (Docker, AWS, Messaging): Helps with Docker configuration, AWS architecture, CI/CD pipelines, Kubernetes, monitoring, and messaging infrastructure (Kafka, SQS, SNS). Use whenever the user wants to review or create Dockerfiles, docker-compose configs, AWS architecture, CI/CD pipelines…
tiny-web-crawler
Crawl from one or more starting web pages, fetch readable content, search within pages, follow relevant links, and stop when the requested information is found or a bounded limit is reached.
swift-concurrency-pro
Reviews Swift code for concurrency correctness, modern API usage, and common async/await pitfalls. Use when reading, writing, or reviewing Swift concurrency code.
frontend-feature
Build a new page, view, or data-driven feature in the Next.js frontend. Use when adding a route under the dashboard/marketing area, wiring UI to a backend endpoint, adding client state, or creating a localized page. Covers App Router, data fetching, Zustand stores, and i18n.