data-corrections-writer

data-corrections-writer is a skill for Claude Code from ur-grue/autopunk-media-skills. It costs 45 tokens per session (1,101 once invoked), scanned A, original, MIT.

A writing aid for drafting formal notices that correct incorrect figures in published articles.

In plain words
What is it for?
Use it to prepare a corrections notice for an editor or legal team after a confirmed data error.
Why use it?
It helps explain exactly what was wrong, what the correct figure is, and whether the mistake changed the article’s conclusions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the autopunk-media-skills plugin — 187 skills shipped together

Good fit Use it to prepare a corrections notice for an editor or legal team after a confirmed data error.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ur-grue/autopunk-media-skills/data-corrections-writer
Install

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.

Any agent
npx skills add ur-grue/autopunk-media-skills --skill data-corrections-writer
Clone the repo
git clone --depth 1 https://github.com/ur-grue/autopunk-media-skills

Made for: Claude Code.

Or install autopunk-media-skills, the plugin that ships this one along with the rest of its 187 skills.

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 data-corrections-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/data-corrections-writer/github.svg)](https://agentmods.dev/skills/ur-grue/autopunk-media-skills/data-corrections-writer)
Your own site
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/data-corrections-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/data-corrections-writer/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 data-corrections-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/data-corrections-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/data-corrections-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,101 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00045 $0.01101
Opus 5 $0.00023 $0.00550
Sonnet 5 $0.00009 $0.00220
Haiku 4.5 $0.00005 $0.00110

Measured 12d ago against content hash a207daa6045f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

data-corrections-writer 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.

skills/data-journalism/publishing/data-corrections-writer/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Corrections Writer

What This Skill Does

Writes a precise, publication-standard corrections notice for a data error published in an article — stating clearly what was wrong, what the correct figure is, and how the error affected the reported story.

When To Use This Skill

  • A data error has been identified in a published article and needs a formal correction notice
  • You need to word a correction that is honest about the scope of the error without overstating its impact on the story's conclusions
  • A reader or subject has disputed a figure and you have confirmed the error
  • An editor or legal team needs a corrections draft to review before publication

What You Need To Provide

Required: The original published figure (as it appeared in print or online). The correct figure. The article headline or title and publication date. A brief explanation of how the error occurred (if known — this can be "we do not know how this error occurred"). Optional: Whether the error affects the story's main conclusion (yes / no / partially); whether a related chart, table, or infographic also needs correction; the publication's standard corrections format or style.

How the Assistant Approaches This

  1. Drafts a correction that states the error precisely — the original figure, the correct figure, and where in the article it appeared — without defensive language or over-explanation.
  2. Assesses whether the correction should include a note on whether the story's core finding is affected, and drafts appropriate language: affirming the conclusion stands, or acknowledging that it changes.
  3. Produces the correction in the standard form: present tense, direct, no passive constructions that obscure responsibility.

Output Format

A corrections notice of two to five sentences. Standard structure: (1) The article title and date, (2) what was wrong and where it appeared, (3) what the correct figure is, (4) whether the error affects the article's conclusions. Optionally: a note on what caused the error if this is known and disclosable. Tone: direct, factual, no hedging. Plain language.

Read the full file on GitHub · 68 lines

Files

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.

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. 12d ago First seen · 68 lines · 45 tokens per session scan A a207daa6045f

Subscribe to this mod's changes

data-corrections-writer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 11d ago), licensed MIT. It adds 45 tokens to every session and 1,101 once invoked, about $0.0002 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.