Borrowing it
Nothing to install: this file belongs to AHepi/DeepReason. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AHepi/DeepReason/main/.claude/skills/pinker-clarity-workflow/SKILL.mdgit clone --depth 1 https://github.com/AHepi/DeepReasonWrote 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/ahepi/deepreason/pinker-clarity-workflow)<a href="https://agentmods.dev/skills/ahepi/deepreason/pinker-clarity-workflow"><img src="https://agentmods.dev/badge/skills/ahepi/deepreason/pinker-clarity-workflow.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 | $0.00092 | $0.01156 |
| Opus 5 | $0.00046 | $0.00578 |
| Sonnet 5 | $0.00018 | $0.00231 |
| Haiku 4.5 | $0.00009 | $0.00116 |
Grade A, and why
pinker-clarity-workflow 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pinker Clarity Workflow
Produce reader or learner understanding before polishing expression. Apply Pinker's communication principles without impersonating him or treating his entire worldview as a style guide.
Route the request
Identify the operating mode from the requested outcome:
- Method: Explain how to teach, how to write, or how the two fit together. State which guidance Pinker directly gives and which guidance this workflow derives from his work.
- Teaching: Use
$pinker-teach-for-understandingfor an explanation, lesson, course sequence, tutoring exchange, or teaching audit. - Writing: Use
$pinker-write-for-readersfor a draft, revision, writing lesson, or prose audit. - Teaching artifact: Apply teaching first to decide what the learner must understand, then writing to shape the handout, script, lecture, chapter, or worked example.
- Research about Pinker: Read references/research-map.md. Verify time-sensitive claims against current primary sources.
If a companion skill cannot be loaded, follow the compact mixed workflow below rather than stopping.
Establish the communication contract
Determine the real-world subject, intended audience, desired change in understanding or ability, medium, length, register, and non-negotiable content. Infer ordinary details when safe. Ask only when a missing choice would materially change the result.
Treat the audience as intelligent but not already initiated into the writer's or teacher's guild. Record what they likely know, what they need next, and which terms or premises may be invisible to an expert.
Run the mixed workflow
- Ground truth. Extract the claims, evidence, distinctions, uncertainties, and source constraints. Research missing or current facts before drafting. Fluency is not evidence.
- Name the destination. State what the audience should be able to explain, predict, distinguish, decide, or do afterward.
- Build the model. Start from a phenomenon, problem, puzzle, or consequential question. Organize the few ideas that explain it. Separate the best current conclusion from live uncertainty.
- Bridge the knowledge gap. Pair each important generalization with a concrete example. Define necessary terms at first useful contact. Supply hidden premises and identify pronoun or acronym referents.
- Test understanding. Require paraphrase, prediction, comparison, application, or a counterexample when interaction permits. Do not use assent or smooth repetition as the test.
- Shape the prose. Put the problem before its solution, keep the topic visible, make relations between sentences recoverable, and prefer actors and actions when abstractions hide them.
- Test the communication. Seek feedback from a representative reader or learner when available. If no human test occurred, say so and provide targeted test questions instead of claiming validation. For a standalone learner-facing artifact, put that disclosure in the handoff note rather than interrupting the artifact itself.
- Revise. Repair the content model before local wording. Then revise coherence, syntax, context, concision, rhythm, and usage in that order.
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 First seen · 59 lines · 92 tokens per session scan A e2cace23e551
pinker-clarity-workflow is a skill published in the GitHub repository AHepi/DeepReason (142 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 1,156 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
master-yinguang
Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…