Agent skill

Writing Guidelines

by fcakyon in fcakyon/claude-codex-settings

This skill should be used when the user asks to "review writing", "check documentation style", "audit interface copy", or "apply writing guidelines".

MITAuto-check passedWriting & Content

Install Writing Guidelines

skills CLI
$ npx skills add fcakyon/claude-codex-settings --skill writing-guidelines -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install fcakyon/claude-codex-settings writing-guidelines --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/fcakyon/claude-codex-settings.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/frontend-design-skills/skills/writing-guidelines .claude/skills/writing-guidelines && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
writing-guidelines
GitHub stars
1.2k
Token cost
~3.6k tokens
SKILL.md length
1,743 words
Files
1
Skills in repo
43
Repo updated
First seen
Licence
MIT

At a glance

This skill should be used when the user asks to "review writing", "check documentation style", "audit interface copy", or "apply writing guidelines".

  • Asks to review writing
  • SKILL.md covers Rules and Output Format
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Check documentation style

What it does

Writing Guidelines is an agent skill from fcakyon/claude-codex-settings. This skill should be used when the user asks to "review writing", "check documentation style", "audit interface copy", or "apply writing guidelines".

Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Brand voice and tone. The repository describes itself as: Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support. The licence is MIT.

When your agent uses it

  • Asks to review writing
  • Check documentation style
  • Audit interface copy
  • Apply writing guidelines

Example prompts

  • “review writing”
  • “check documentation style”
  • “audit interface copy”
  • “/writing-guidelines”

What it can do on your machine

Read from SKILL.md and the folder at commit 7a519d8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Writing Guidelines loads about 3.6k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 1,743 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~3.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from fcakyon/claude-codex-settings at commit 7a519d8, republished under its MIT licence (© fcakyon). 1,743 words, ~3,556 tokens.

Download SKILL.mdSave it as .claude/skills/writing-guidelines/SKILL.md (or your agent's skills folder).
name
writing-guidelines
description
This skill should be used when the user asks to "review writing", "check documentation style", "audit interface copy", or "apply writing guidelines".
metadata.argument-hint
<file-or-pattern>
license
MIT

Writing Guidelines

Review the files or patterns provided by the user for compliance.

Read files, check against rules below. Output concise but comprehensive: sacrifice grammar for brevity. High signal-to-noise.

Rules

Planning & content type
  • Every page has a plan (overview, goal, audience, content plan, open questions) referenced or linked
  • Content type declared in meta.contentType: Tutorial, How-to, Reference, Conceptual, Troubleshooting, or Landing
  • Title is user-shaped (the user's question), not feature-shaped (the engineer's name)
  • Page does one job: tutorial OR how-to OR reference, not three at once
  • Goal is verb-driven (Bloom's taxonomy): "configure", "explain", "debug" (testable)
  • Multi-audience pages: short shared opener, then technical subsections
Voice & tone
  • Active voice. Mental test: append "by monkeys". If the sentence parses, rewrite
  • Direct address: you, never the user or one can
  • Imperative for steps: "Click Add Project", not "You will need to click Add Project"
  • Sentences under 20 words target
  • Contractions encouraged (you'll, it's) for warmth
  • Present tense unless describing future behavior
  • Limit we: only for deliberate organization actions ("we recommend", "we deprecated"), never as a stand-in for "you"
  • No rhetorical questions (sounds like marketing)
  • Second-read test: read each sentence once at speech pace; if you re-read to parse it, name the subject, the action, and the consequence (kill metaphor verbs and pronouns reaching back several sentences)
Banned words
  • easy, simple, quick: puts pressure on the reader and reads as marketing; replace with concrete description ("one command", "default settings", "most projects don't need this")
  • very, just, really: filler; cut or rewrite
Concision
  • Earn every detail: cut a number, name, or implementation detail if a more general phrasing wouldn't change the reader's understanding or action
  • Weasel words: replace vague qualifiers (significantly, many, often, typically, generally) with a specific number or claim
  • Vague quantifiers: no near-zero, sub-second, most requests; give the figure and cite it (99.37% of requests see zero cold starts)
  • Filler/metaphor verbs: name the action instead of reaching for cadence (moves through, lands, carries, hits → the literal step)
AI-generated tells (flag these)
  • Summary-style transitions: never open a paragraph by recapping the last one (With this setup complete…, Now that we've explored…); pivot straight to the next point (In practice…, The catch is…)
  • Stop-start sentences: don't split one dependent idea into choppy fragments (Previously this was manual. Now it's automatic. This saves time. → one sentence); short sentences for emphasis are fine
  • Spec-sheet voice: rewrite sentences that read like a system reading a datasheet (provides, is configurable, is explicitly labeled)
  • Cold-open paragraphs: a body paragraph whose first sentence works as a standalone heading has no antecedent; carry the prior subject forward (Because…, Once…)
  • Personified artifacts: machines don't perform human-physical actions (hand the browser a URL → the browser fetches the URL; the token holds… → the token is stored…)
  • Reused framing: the angle must come from this page, not a template (The question most teams face is whether…)
Tone, by content type
  • Tutorial: warm, encouraging, predictable structure, no traps
  • How-to: terse, direct (reader is mid-task)
  • Reference: neutral, exhaustive, quotable
  • Conceptual: explain like the reader will teach it back; examples and analogies welcome
  • Troubleshooting: empathetic but not apologetic; acknowledge then fix
Headings
  • Sentence case for page headings (H1 H2 H3): "Configure environment variables", not "Configure Environment Variables"
  • Title case for nav labels: "Configuring Environment Variables"
  • meta.title becomes the H1; meta.navLabel becomes the sidebar entry
  • Subheadings descriptive, not cute: "Caveats when self-hosting on Cloudflare", not "Caveats"
  • Reader should be able to guess section content from the heading alone
Structure
  • Every page opens with a one-paragraph TL;DR of what the page covers
  • Every major section opens with a summary sentence
  • Acronyms spelled out on first use: "Content Security Policy (CSP) blocks inline scripts"
  • Define every term the first time you use it (link to its conceptual page)
  • Reference docs organized by surface; education docs organized by reader task
  • Keep paragraphs to 2 to 4 sentences; split anything longer or covering two ideas
Lists
  • Three or more list-shaped items in a paragraph: convert to a list
  • Bulleted for unordered; numbered for ordered (lifecycles, sequential steps)
  • Always introduce a list with a colon
  • No periods at the end of list items unless they are full sentences
  • Bold/description format: - **Term**: description here (colon after bold term)
Code
  • Code blocks need a language tag for syntax highlighting
  • TypeScript is the default for new code unless the surface is genuinely language-agnostic
  • Multi-step flows wrapped in <Steps/> so structure is visible
  • Highlight load-bearing lines: ```typescript {8-12,23-37}
  • ≤80 columns per line in snippets
  • ≤25 lines per snippet; split longer blocks with prose
  • Omit defaults; don't repeat variable definitions, use shared var
  • Minimal comments in code blocks; prefer prose explanation
  • Explain what every code block does in prose (don't drop and run)
  • Don't reference full example files at the end of guides ("See train.py"); the guide is the deliverable
Placeholders
  • Text placeholders: snake_case, descriptive: your_access_token_here (so reader can double-click to select before pasting)
  • Number placeholders: count up 1234567890123 (recognizable as fake, predictable)
  • Never <TOKEN>, xxx, your-token, or generic ALL_CAPS
Data sizes & units
  • Space + uppercase unit: 64 KB, 5 KB, 200 ms
  • Exception: seconds is bare: 30s
  • Consistent across the corpus so readers can develop scanning habits
Money & pricing pages
  • Uncompromising detail: err on "too much"
  • Use tables for pricing
  • Never assume reader knows the pricing model or whether their workload counts as one invocation or several
  • Clarity and transparency above all else
Emphasis
  • Bold means UI element or critical fact, never emphasis-for-emphasis-sake
  • Reaching for bold for tone: the sentence is weak; rewrite it
  • Inline code for paths, file extensions, identifiers, short snippets: /api, .tsx, body, query, req
  • Rule: if it would look weird without a monospace font, monospace it
Punctuation & typography
  • Never em dashes (—) or dashes (-) as punctuation; use colons, commas, periods, or rephrase
  • Curly quotes " " and ' ', not straight " or '
  • Ellipsis …, not three dots ...
  • Loading states end with …: Loading…, Saving…
  • Non-breaking spaces in 10&nbsp;MB, ⌘&nbsp;K, brand names
  • & over "and" only where space-constrained (nav labels, buttons)
Source formatting
  • Don't hard-wrap paragraphs: each paragraph is one line in source, let the editor wrap
  • One blank line before headings; one blank line before and after code blocks
  • No --- horizontal rules between sections
  • No extra blank lines between elements that aren't paragraph breaks
Show full SKILL.md (726 more words)Show less
  • Define every term the first time it appears, link to its conceptual page
  • Anchor text names the destination; never bare URLs or here/link
  • Dashboard links should open the exact destination and preserve required context in the URL.
  • Link to canonical product documentation when relevant.
  • Link to the canonical model catalog for the selected provider when examples name models.
Models in examples
  • Always use the latest model strings: anthropic/claude-opus-4-7, not anthropic/claude-sonnet-4 or older
  • For image generation default: google/gemini-3.1-flash-image-preview
AI workflow
  • You are accountable for the content you produce, however it is created
  • You are the final arbiter; the model proposes, you dispose
  • Hold technical accuracy to a high standard: docs are also consumed by LLMs, wrong docs train wrong models
  • Use only enterprise models that do not train on your data (especially for unreleased products)
  • Disclose AI use in the PR (model + prompts if useful)
  • Plan first by hand; the plan is the spec the model works against
  • Use plan-mode in your editor (Cursor, Claude) before letting the model write
  • Tell the model to follow AGENTS.md and the linting checklist
  • Run a test prompt against the preview: "given this plan's goal, can the model complete the task using only this page?"
  • Final human review always
Quality checklist (required boxes are non-negotiable)
  • Findability: sidebar bucket set via meta.category; UI links to docs from any dashboard surface that exposes the feature
  • Accuracy: code samples actually run; screenshots map 1:1 to current UI and use the ACME demo account
  • Relevance: code samples included where applicable (TypeScript first; <Steps/> for multi-step flows)
  • Clarity: overview addresses who/what/where/why; high-level use cases laid out; quickstart for new products; prerequisites listed on tutorials; a sample repository for multi-step tutorials; steps detailed not vague; visual aids in confusing sections; simplest path recommended when multiple exist
  • Completeness: limits documented; all-limits tables updated; content plan followed and goals addressed
  • Readability: nav names scannable and use action verbs; content types accurately used; subheadings descriptive; topics start with summaries; code blocks formatted correctly; active voice where warranted
Review
  • PR description links to the content plan, lists what to review, and links the preview URL
  • Ping the team via the PR link (not the plan or preview directly)
  • Author is accountable, not the reviewer; reviewers are liberal with approvals
  • Suggestion comments for small text fixes; preview comments for anything bigger
  • Disagreement is fine; reject with a one-line reason and move on
Anti-patterns (flag these)
  • Em dashes (—) or dashes (-) used as punctuation
  • easy, simple, quick describing reader actions
  • Passive voice (apply "by monkeys" test)
  • Title Case in page headings (only sentence case in H1 through H6)
  • Generic placeholders: <TOKEN>, xxx, your-token, ABC123
  • Code blocks without a language tag
  • JS examples where TypeScript is the convention
  • Code blocks over 25 lines without prose between
  • Hard-wrapped prose paragraphs (multiple lines for one paragraph in source)
  • --- horizontal rules between sections
  • Subheadings that are single generic words: Overview, Caveats, Notes
  • Bold used for emphasis instead of UI element or critical fact
  • Page or section without an opening summary
  • Straight quotes (", ') instead of curly (", ')
  • Three dots (...) instead of ellipsis (…)
  • Acronyms used before being spelled out
  • Bare unit numbers (64KB, 5kb, 200MS) instead of 64 KB, 5 KB, 200 ms
  • "We" standing in for "you"
  • Rhetorical questions
  • Filler words: very, just, really, simply
  • References to "the full example file at the end of the guide" rather than inlining the code
  • Outdated model strings in examples (anthropic/claude-sonnet-4, gpt-4o, DALL-E)
  • Hardcoded date/number formats instead of Intl.DateTimeFormat / Intl.NumberFormat in code samples
  • "Loading..." instead of "Loading…"
  • Summary-style transitions recapping the previous paragraph (With this setup complete…)
  • Stop-start fragments splitting one dependent idea into choppy sentences
  • Spec-sheet voice reading like a datasheet (provides, is configurable, is explicitly labeled)
  • Cold-open body paragraphs whose first sentence has no antecedent
  • Personified artifacts performing human-physical actions (hand the browser a URL)
  • Reused/template framing not specific to the page (The question most teams face is whether…)
  • Weasel words instead of a specific claim (significantly, many, often, typically, generally)
  • Vague quantifiers without a cited figure (near-zero, sub-second, most requests)
  • Filler/metaphor verbs instead of the literal step (moves through, lands, carries, hits)
  • Sentences that need a second read to parse
  • Paragraphs over 4 sentences or covering two ideas
  • Bare URLs or here/link as anchor text

Output Format

Group by file. Use file:line format (VS Code clickable). Terse findings.

text
## content/docs/sandbox.mdx

content/docs/sandbox.mdx:1 - missing meta.contentType
content/docs/sandbox.mdx:12 - title "Cloud Sandbox" is feature-shaped, not user-question
content/docs/sandbox.mdx:24 - passive voice ("the sandbox is created...")
content/docs/sandbox.mdx:31 - banned word "easy"
content/docs/sandbox.mdx:47 - "..." → "…"
content/docs/sandbox.mdx:58 - code block missing language tag
content/docs/sandbox.mdx:71 - placeholder <TOKEN> → your_access_token_here
content/docs/sandbox.mdx:89 - "64KB" → "64 KB"
content/docs/sandbox.mdx:102 - H2 "Caveats" too generic; add specificity
content/docs/sandbox.mdx:118 - em dash in prose, replace with colon/comma

## content/docs/ai-gateway.mdx

content/docs/ai-gateway.mdx:5 - title case in H1; sentence case only
content/docs/ai-gateway.mdx:18 - acronym AI Gateway used before being spelled out
content/docs/ai-gateway.mdx:34 - bold for emphasis, not UI element
content/docs/ai-gateway.mdx:52 - `anthropic/claude-sonnet-4` outdated; use `anthropic/claude-opus-4-7`
content/docs/ai-gateway.mdx:71 - hard-wrapped paragraph (lines 71-74)

## content/docs/cron.mdx

✓ pass

State issue + location. Skip explanation unless fix is non-obvious. No preamble.

© fcakyon, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/frontend-design-skills/skills/writing-guidelines of fcakyon/claude-codex-settings.

Open the folder on GitHubat commit 7a519d8

Compare with similar skills

Writing Guidelines next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Writing Guidelines compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Writing Guidelines this skillfcakyon/claude-codex-settings1.2k—~3.6kAutomated safety check: PassMIT
Avoid AI Writingconorbronsdon/avoid-ai-writing4.9k3 repos~8.1kAutomated safety check: PassMIT
Khazix WeChat Article WriterKKKKhazix/khazix-skills21k2 repos~2.9kAutomated safety check: PassMIT
BrandOhh-889/skyroc79513 repos~733Automated safety check: PassMIT
Writing Guidelinesvercel-labs/agent-skills32k7 repos~309Automated safety check: PassNone
Unslop AI Writing Cleanuptheclaymethod/unslop512—~1.7kAutomated safety check: PassMIT

Similar skills

  • Avoid AI Writing

    conorbronsdon/avoid-ai-writing

    Audit and rewrite content to remove AI writing patterns ("AI-isms").

    4.9k GitHub starsUsed in 3 repos~8.1k tokens
    Writing & ContentAuto-check passed
  • Khazix WeChat Article Writer

    KKKKhazix/khazix-skills

    Writes long-form WeChat official account articles in the personal style of the Khazix account, from briefs, links, PDFs or rough notes, with a topic quality check.

    21k GitHub starsUsed in 2 repos~2.9k tokens
    Writing & ContentAuto-check passed
  • Brand

    Ohh-889/skyroc

    Brand voice, visual identity, messaging frameworks, asset management, brand consistency.

    795 GitHub starsUsed in 13 repos~733 tokens
    Writing & ContentAuto-check passed
  • Writing Guidelines

    vercel-labs/agent-skills

    Official

    Review docs/prose for Writing Guidelines compliance. An agent skill from vercel-labs/agent-skills.

    32k GitHub starsUsed in 7 repos~309 tokens
    Writing & ContentAuto-check passed
  • Unslop AI Writing Cleanup

    theclaymethod/unslop

    Removes AI writing tells from prose through an audit-first flow, routing to a two-pass rewrite, a report-only cleanup, voice teaching or mimicry depending on the sub-command used.

    512 GitHub stars~1.7k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Brand Voice Guide

    luongnv89/claude-howto

    Ensure all communication matches brand voice and tone guidelines. Use when creating marketing copy, customer communications, public-facing content, or when…

    42k GitHub stars~609 tokensUpdated 8 days ago
    Writing & ContentAuto-check passed

More from fcakyon/claude-codex-settings

All 43 skills in this repo
  • Slides

    fcakyon/claude-codex-settings

    Create and edit presentation slide decks (.pptx) with PptxGenJS, bundled layout helpers, and render/validation utilities.

    1.2k GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed
  • Openobserve API

    fcakyon/claude-codex-settings

    This skill should be used when user asks to "query OpenObserve", "create OpenObserve dashboard", "edit OpenObserve panel", "fetch OpenObserve logs", "run OpenObserve search", "list OpenObserve…

    1.2k GitHub starsUsed in 1 repo~4.1k tokens
    Auto-check passed
  • Supabase JS

    fcakyon/claude-codex-settings

    This skill should be used when user asks to "use supabase-js", "query Supabase database", "supabase auth", "supabase storage", "supabase realtime", "supabase edge functions", or works with the…

    1.2k GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed
  • Yolo Training

    fcakyon/claude-codex-settings

    This skill should be used when user asks to "improve my mAP", "why is my model overfitting", "my training is diverging", "read my results.csv", "interpret my training curves", "my AP50 is good but…

    1.2k GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • Dokploy Deploy

    fcakyon/claude-codex-settings

    This skill should be used when user asks to "deploy with Dokploy", "use Dokploy Cloud", "manage self-hosted Dokploy", "deploy Docker Compose on Dokploy", "manage Dokploy databases", "configure…

    1.2k GitHub stars~891 tokensUpdated yesterday
    Auto-check passed
  • Openship Config

    fcakyon/claude-codex-settings

    This skill should be used when the user asks to "create openship.json", "configure an OpenShip deployment", "make a repo deployable on OpenShip", or fix "openship config validate" errors.

    1.2k GitHub stars~803 tokensUpdated yesterday
    Auto-check passed

Questions about Writing Guidelines

What does Writing Guidelines do?

This skill should be used when the user asks to "review writing", "check documentation style", "audit interface copy", or "apply writing guidelines". Writing Guidelines is an agent skill from fcakyon/claude-codex-settings. This skill should be used when the user asks to "review writing", "check documentation style", "audit interface copy", or "apply writing guidelines".

When should I use Writing Guidelines?

Writing Guidelines fits situations like: asks to review writing; check documentation style; audit interface copy; apply writing guidelines.

How do I install Writing Guidelines in Claude Code?

Run `npx skills add fcakyon/claude-codex-settings --skill writing-guidelines -a claude-code`. Or copy the skill folder (plugins/frontend-design-skills/skills/writing-guidelines in fcakyon/claude-codex-settings) into .claude/skills/writing-guidelines in your project. Claude Code loads it when a task matches its description.

How do I install Writing Guidelines in Codex?

Run `npx skills add fcakyon/claude-codex-settings --skill writing-guidelines -a codex`. Or copy the skill folder (plugins/frontend-design-skills/skills/writing-guidelines in fcakyon/claude-codex-settings) into .agents/skills/writing-guidelines in your project. Codex loads it when a task matches its description.

Can I use Writing Guidelines in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add fcakyon/claude-codex-settings --skill writing-guidelines -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writing-guidelines, .gemini/skills/writing-guidelines, .github/skills/writing-guidelines and .opencode/skills/writing-guidelines in your project.

What does Writing Guidelines need to run?

SKILL.md names no scripts, command-line tools or credentials: Writing Guidelines is instructions for the agent only.

Does Writing Guidelines access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Writing Guidelines safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Writing Guidelines use?

Writing Guidelines is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Writing Guidelines use?

About 3.6k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Writing Guidelines?

Skills that share tags, products or a category with Writing Guidelines: Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars), Khazix WeChat Article Writer (KKKKhazix/khazix-skills, 21k stars), Brand (Ohh-889/skyroc, 795 stars) and Writing Guidelines (vercel-labs/agent-skills, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Writing Guidelines?

fcakyon (a GitHub user) maintains it in fcakyon/claude-codex-settings, which has 1,165 GitHub stars. The repository holds 43 skills in this directory. The repository was last updated on October 7, 2026.

Source: fcakyon/claude-codex-settings on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.