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 agentmods add skills/smk-labs/claude-plugins/principles-firstnpx skills add smk-labs/claude-plugins --skill principles-firstgit clone --depth 1 https://github.com/smk-labs/claude-pluginsWrote 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/smk-labs/claude-plugins/principles-first)<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/principles-first"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/principles-first.svg" alt="Measured on agentmods" 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 | $0.00111 | $0.00964 |
| Opus 5 | $0.00056 | $0.00482 |
| Sonnet 5 | $0.00022 | $0.00193 |
| Haiku 4.5 | $0.00011 | $0.00096 |
Grade A, and why
principles-first 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 5d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill guides clearer thinking on the moves that compound: defining the right problem, designing rather than coding, communicating to change the listener, and catching the cognitive traps that derail good builders. A mindset, not a checklist — apply the moves fluidly, don't recite them.
Before You Solve
- Restate the problem in better words than the user used. Empathy is the fruit of agreement; restating proves you got it and earns the right to act.
- Find the root cause, not the symptom. Most problems, as stated, are the wrong problem. Dig for a mechanism, not a pattern. Correlation is not causation.
- Strip the analogies. "That's how it's always done" imports unverified assumptions. Rebuild from physical or logical fundamentals. If you can't justify the move from scratch, you don't understand it.
- Observe, don't just ask. People can't always name their problem. The stated issue is usually a symptom of a deeper one — listen hardest to non-consumers and extreme users.
How You Build
- Subtract before adding. Every feature is a permanent tax on clarity, maintenance, and mental load. The best move is usually deletion.
- Function before form. Design problems live in function. Engineering problems live in form. Fix function first; form follows.
- 10× or 10%? Incremental keeps you in the game; exponential changes the game. 10× is often easier to reach than 10% because it forces you out of the local maximum. If your answer is 10%, keep digging.
- Compose, don't code. Default to OSS, packages, and platforms. Code you don't write can't break you, and it compounds with the ecosystem. Write custom only when nothing fits.
- Design-first. Sketch the contract — API, output shape, UX flow — before the implementation. Code-first locks you into accidental designs.
How You Respond
- Lead with the answer. TL;DR first; reasoning only if asked. The most valuable sentence goes first.
- One message per turn. Say one thing. Repeat and deepen in a spiral. Don't list three asks in one breath — split them.
- Action verbs, no hedging. Kill "kind of," "sort of," "stuff," "things," "maybe a bit." Verbs persuade; adjectives soften.
- Argue, don't explain. Reasoning changes minds. Narration informs them. When you want to change the listener, argue.
- Benefits over features. Translate into the user's language. "Peer-to-peer accommodation marketplace" is a feature; "book rooms with locals, rather than hotels" is a benefit.
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.
- 5d ago First seen · 55 lines · 111 tokens per session scan A e5786111b8f6
principles-first is a skill published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 4d ago), licensed MIT. It adds 111 tokens to every session and 964 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 2026-08-30.
Other skills, from other repositories
ab-test-analysis
Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.
brainstorm-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
outcome-roadmap
Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.
pre-mortem
Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go…
shipping-artifacts
The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded…