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 jonZlotnik/how-to-agent --skill concrete-over-figurativegit clone --depth 1 https://github.com/jonZlotnik/how-to-agentWrote 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/jonzlotnik/how-to-agent/concrete-over-figurative)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/concrete-over-figurative"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/concrete-over-figurative/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/jonzlotnik/how-to-agent/concrete-over-figurative"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/concrete-over-figurative.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 | $0.00050 | $0.00615 |
| Opus 5 | $0.00025 | $0.00308 |
| Sonnet 5 | $0.00010 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
concrete-over-figurative 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concrete Over Figurative
Technical prose exists to transfer facts, and metaphor makes the reader interpret an image before reaching the fact. "Excavate the requirement" means "identify the requirement". "A load-bearing assumption" means "an assumption the design depends on". The literal version costs nothing to decode, translates across languages and readers, and states exactly one thing.
When to use
- A verb is an image: excavate, surface, sprout, bubble up, drill down, journey
- A qualifier is intensity without measurement: "blazing fast", "rock solid", "massive"
- A reviewer or reader asks what a phrase means
- Text will be read by non-native speakers or by agents matching on descriptions
Protocol
- Find the images. Read the text for words describing physical actions or objects that are not literally present.
- State what each image stands for. "The config sprouts conditionals" → "the config accumulates conditionals". If no literal statement exists behind the image, the sentence has no content — delete it.
- Replace intensity with facts you have — never invent them. If a measurement exists in the code, a benchmark, or your own observation, use it: "huge file" → "a 2 GB file". If no measurement exists, do not fabricate one: delete the intensity claim, name its source, or ask. An invented number is worse than a vague word — the vague word is visibly vague, while the invented number looks authoritative.
- Re-read for residue. If any remaining term requires the reader to interpret an image, replace it and read again.
Example
Before: Excavate the real need — treat every load-bearing assumption
with care before the design calcifies.
After: Identify the real need. Confirm every assumption the design
depends on before the design becomes expensive to change.
Red flags (rationalizations to reject)
- "It reads as boring without style." — Reference prose earns nothing from style. It earns from precision.
- "Everyone knows the metaphor." — Non-native readers, newcomers, and routing agents do not.
- "The image explains it faster." — Then keep the image and state the literal fact. Never the image alone.
- "A specific number reads better." — Only when it is real. A fabricated measurement is a correctness bug dressed as style.
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 · 45 lines · 50 tokens per session scan A 0f04510c6aa2
concrete-over-figurative is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 615 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…