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 deciqAI/knowledge-skills --skill do-things-that-dont-scalegit clone --depth 1 https://github.com/deciqAI/knowledge-skillsWrote 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/deciqai/knowledge-skills/do-things-that-dont-scale)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/do-things-that-dont-scale"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/do-things-that-dont-scale/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/deciqai/knowledge-skills/do-things-that-dont-scale"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/do-things-that-dont-scale.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 | $0.00089 | $0.00666 |
| Opus 5 | $0.00044 | $0.00333 |
| Sonnet 5 | $0.00018 | $0.00133 |
| Haiku 4.5 | $0.00009 | $0.00067 |
Grade A, and why
do-things-that-dont-scale 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Do Things That Don't Scale
Overview
Paul Graham's counterintuitive rule: early on, the unscalable is exactly what you should do. Startups don't take off by themselves — founders recruit users manually, deliver an over-the-top experience by hand, and learn things automation would hide. Worrying about scale too early is a form of avoidance; the manual phase is where you earn insight and love that later become your moat.
The Process
- Recruit the first users by hand — go to them individually; don't wait for a funnel. Gate: "it won't scale" used to avoid direct outreach = you're hiding from the work that matters now.
- Deliver a delightfully unscalable experience — concierge/white-glove; do manually what the product will later automate.
- Insert yourself into the value delivery — the friction you feel is the product spec.
- Learn from doing, not dashboards — hand-delivery surfaces needs analytics miss.
- Use the unscalable to create early love — a small number of users who love you beats many who are indifferent.
- Systemize only what's validated — automate a step after manual delivery proves it matters. Gate: automating before validation locks in the wrong process (and becomes an agent doing the wrong thing well).
When to Use
- Pre-PMF user acquisition and delivery
- Tempted to build automation before demand is proven
- Early service businesses deciding manual vs systemized
Applying It Well
- Manual now buys the insight that makes later automation correct.
- The best unscalable move is usually direct, personal, and generous.
- Feeds systemization later — do it by hand, then write the SOP (see sop-systemization).
Red Flags
- Building automation/funnels before anyone loves the manual version.
- "Won't scale" as an excuse to avoid sales/support.
- Optimizing efficiency before validating the motion.
Verification
- First users recruited personally
- Early delivery done manually/concierge
- Insights captured from hands-on delivery
- Automation deferred until the step is validated
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 · 44 lines · 89 tokens per session scan A 4b6b6e69c728
do-things-that-dont-scale is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 7d ago), licensed MIT. It adds 89 tokens to every session and 666 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 2026-08-31.
Other skills, from other repositories
edge-tts
Text-to-speech conversion using uvx edge-tts for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS…
mcp-deepwiki
Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.
tianqi
A weather-lookup workflow for Chinese locations, covering forecasts, hourly conditions, weather warnings, and daily-life indexes.
cto-advisor
Records technical decisions that serve a business outcome: constraints, architecture options, build-or-buy tradeoffs, and a justified skill selection. Use when the CEO asks "which architecture fits", "should we build or buy", "which skill should this department use", or "review our technical plan".
maishou
A price-comparison workflow for products sold through major Chinese online marketplaces. It searches listings and can retrieve product details, purchase links, and available coupons.
compliance-check
Compliance pre-flight for a feature, campaign, or initiative — maps the data and activity involved, checks applicable regimes (privacy/GDPR-style, consumer protection, marketing rules, sector-specific), lists required approvals and notices, builds a gap list with remediation owners, and ends in a go/no-go…