teach-revision

teach-revision is a skill for Claude Code from OC-NeuralSense/reader-first-writing-skills. It costs 166 tokens per session (1,872 once invoked), scanned A, original, Apache-2.0.

A teaching method for improving a learner's own draft by making each editing decision visible.

In plain words
What is it for?
It is for guided revision of drafts when the learner wants to build reusable writing skills.
Why use it?
It helps writers understand what is wrong, how to test for it, and why a particular revision works instead of receiving an unexplained rewrite.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the reader-first-writing plugin — 12 skills, 3 agents shipped together

Good fit It is for guided revision of drafts when the learner wants to build reusable writing skills.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add OC-NeuralSense/reader-first-writing-skills
Claude Code
/plugin install reader-first-writing

Made for: Claude Code.

Or install reader-first-writing, the plugin that ships this one along with the rest of its 12 skills, 3 agents.

Wrote 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.

agentmods badge for teach-revision

README.md
[![agentmods](https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/teach-revision/github.svg)](https://agentmods.dev/skills/oc-neuralsense/reader-first-writing-skills/teach-revision)
Your own site
<a href="https://agentmods.dev/skills/oc-neuralsense/reader-first-writing-skills/teach-revision"><img src="https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/teach-revision/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.

agentmods 80×15 button for teach-revision

Your own site · 80×15
<a href="https://agentmods.dev/skills/oc-neuralsense/reader-first-writing-skills/teach-revision"><img src="https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/teach-revision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 166 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,872 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00166 $0.01872
Opus 5 $0.00083 $0.00936
Sonnet 5 $0.00033 $0.00374
Haiku 4.5 $0.00017 $0.00187

Measured 11d ago against content hash 6c7c2cec7707, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

teach-revision 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 11d 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.

skills/teach-revision/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

teach-revision

Purpose

Improve a draft in a way whose product is not just a better document but a more capable writer. Instead of quietly fixing the draft and handing it back, stage the revision so every move is visible and reusable. Each move names three things: the defect, the concrete test that revealed it, and the principle behind the fix. The aim is that the learner could run the same test unaided next time.

When to use

  • A learner supplies their own draft and wants to understand why the edits work.
  • The intent is pedagogical: build the writer's judgment, not just clean the page.

When NOT to use (routing non-triggers)

  • The writer just wants the document fixed, not taught -> the revise-* skills.
  • The writer wants a graded verdict or ship decision -> review-document.
  • The writer wants two versions compared -> compare-versions.

Inputs

  • learner_draft (required)
  • learner_level (novice | mixed | practitioner | expert: sets pace and how much is shown per move)
  • reader-frame contract (required: every defect is defined relative to this reader)

Workflow (each move is defect + test + rationale)

  1. Diagnose, don't dump. Find the faults, then select the few worth teaching; a revision annotated to death teaches nothing.
  2. For each selected move, name the defect. State precisely what is wrong and where.
  3. Show the test that reveals it. Give a concrete, re-runnable check (e.g. "ask who?: if more than one antecedent fits, the pronoun is ambiguous"), not a vibe.
  4. Apply the fix visibly. Make the edit, but never silently: the learner sees the before, the after, and the move between them.
  5. Attach the principle. Explain the reader effect the fix produces (the reason the move works) without the generic "this is just better" gloss.
  6. Check the learner could re-apply the test. If not, the move was not yet a teaching; simplify it.

Decision rules

  • Nothing is repaired silently. "I changed this to that" teaches one edit; a named test teaches a reusable skill.
  • Do not overwhelm; pick the highest-value moves for the learner's level.
  • Do not present one form as the single correct one; good writing takes several valid shapes. Teach judgment, not a house style.
  • Every move carries a real, testable reason. A reason the learner cannot test is not yet a teaching.

Read the full file on GitHub · 142 lines

Changes

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.

  1. 11d ago First seen · 142 lines · 166 tokens per session scan A 6c7c2cec7707

Subscribe to this mod's changes

teach-revision is a skill published in the GitHub repository OC-NeuralSense/reader-first-writing-skills (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 166 tokens to every session and 1,872 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

using-dinf

WHAT: the D∞ notation — the ⟨parts | Ω⟩ shape every durable teaching, framework, plan, and joke has — plus the three operators over it (FACTOR, ADJOIN, CHRISTEN) and the dinf CLI that makes the missing-closure defect machine-catchable. WHEN: when stuck; when a plan feels like unjoined parts; when two frames are…

sancovp/dinf · 118 tokens

debate-orchestrator

Orchestrates formal debates with proposition and opposition sides, coordinating debaters and judges through structured exchanges. Use when running debate exchanges, managing debate rounds, or continuing interrupted debates.

urav06/dialectic · 41 tokens

tokenomics-method

Use when a builder wants to learn or be reminded of the tokenomics method: spending model capability like a scarce budget through tiered routing, spec-based handoffs, and a living playbook. Teaches the thesis, the four layers, the four switchpoints, the routing test, and the lane-scarcity rule. Pure knowledge; takes…

slopstopper/tokenomics · 76 tokens

elixir-idioms

OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.

oliver-kriska/claude-elixir-phoenix · 44 tokens

engineering-onboarding

Create an onboarding guide for an engineer joining a team that consumes the design system. Trigger when someone says: onboard new engineer, developer getting started guide, new engineer guide, engineering onboarding, first day for developers, frontend onboarding, or anything about helping an engineer new to the team…

murphytrueman/design-system-ops · 68 tokens

async-learning-teacher

Transform saved links, papers, articles, posts, videos, and reference collections into approachable AI teaching artifacts for later study. Use when a user wants to queue learning material, create a readable explanation from a source, teach a paper or post step by step, or run an interactive tutor that validates…

tamdogood/builder-essential-skills · 68 tokens