Agent skill

Code Prose

by EpicenterHQ in EpicenterHQ/epicenter

Apply Orwell's rules to the prose inside code — identifiers and comments — without changing behavior.

Custom licenceAuto-check passed

Install Code Prose

skills CLI
$ npx skills add EpicenterHQ/epicenter --skill code-prose -a claude-code

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

GitHub CLI
$ gh skill install EpicenterHQ/epicenter code-prose --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/EpicenterHQ/epicenter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/code-prose .claude/skills/code-prose && 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
code-prose
GitHub stars
4.8k
Token cost
~607 tokens
SKILL.md length
336 words
Files
1
Skills in repo
65
Repo updated
First seen
Licence
Custom licence

At a glance

Apply Orwell's rules to the prose inside code — identifiers and comments — without changing behavior.

  • Works in 3 steps: One word per concept, one concept per… → Cut words the context already carries. A… → A compound name is usually a hedge
  • Comments need an editorial pass
  • SKILL.md covers Word choice in code and comments and Overfitting
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Code Prose is an agent skill from EpicenterHQ/epicenter. Apply Orwell's rules to the prose inside code — identifiers and comments — without changing behavior. Use when names, word choice, or comments need an editorial pass.

Its SKILL.md is about 610 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Open-source, local-first apps.

When your agent uses it

  • Comments need an editorial pass

Example prompts

  • “/code-prose”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. One word per concept, one concept per word. Keep a vocabulary. If sync names "pulling remote changes," it cannot also name "flushing edits…
  2. Cut words the context already carries. A module named workspaceWatcher does not need startNativeWorkspaceWatcher; watchWorkspace says the…
  3. A compound name is usually a hedge

What it can do on your machine

Read from SKILL.md and the folder at commit 9cc65c3. 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

Code Prose loads about 607 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 336 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~607

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 336 words (~607 tokens).

“Review changes in the current branch, or in the scope the user specifies. Apply these criteria without changing behavior. Only touch code in that scope, and run the relevant existing checks after changes.”

— opening of SKILL.md by EpicenterHQ, Custom licence
name
code-prose

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/code-prose of EpicenterHQ/epicenter.

Open the folder on GitHubat commit 9cc65c3

Compare with similar skills

Code Prose 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.

Code Prose compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Prose this skillEpicenterHQ/epicenter4.8k—~607Automated safety check: PassCustom licence
Prosestatic-web-server/static-web-server2.4k—~971Automated safety check: PassApache-2.0
Beautiful Prosesickn33/agentic-awesome-skills47k2 repos~1.4kAutomated safety check: PassMIT
Identifybrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~1.3kAutomated safety check: PassCustom licence
Identify Assumptions Existingphuryn/pm-skills27k—~525Automated safety check: PassMIT
Identify Assumptions Newphuryn/pm-skills27k—~807Automated safety check: PassMIT

Similar skills

  • Prose

    static-web-server/static-web-server

    Author or edit any prose for the Static Web Server (SWS) project — documentation, design docs, READMEs, PR descriptions, issue bodies, commit message bodies, or other human-readable text — following…

    2.4k GitHub stars~971 tokensUpdated today
    DevelopmentAuto-check passed
  • Beautiful Prose

    sickn33/agentic-awesome-skills

    A hard-edged writing style contract for timeless, forceful English prose without modern AI tics.

    47k GitHub starsUsed in 2 repos~1.4k tokens
    Writing & ContentAuto-check passed
  • Identify

    brycewang-stanford/Auto-Empirical-Research-Skills

    Design or review identification strategy for the sewage-house-prices project.

    4.5k GitHub stars~1.3k tokensUpdated 3 days ago
    Research & ScienceAuto-check passed
  • Identify risky assumptions for a feature idea in an existing product across Value, Usability, Viability, and Feasibility.

    27k GitHub stars~525 tokensUpdated 23 days ago
    Frontend & DesignAuto-check passed
  • Identify Assumptions New

    phuryn/pm-skills

    Identify risky assumptions for a new product idea across 8 risk categories including Go-to-Market, Strategy, and Team.

    27k GitHub stars~807 tokensUpdated 23 days ago
    Marketing & SEOAuto-check passed
  • Detecting Insider Threat Behaviors

    mukul975/Anthropic-Cybersecurity-Skills

    Detect insider threat behavioral indicators including unusual data access, off-hours activity, mass file downloads, privilege abuse, and resignation-correlated data theft.

    34k GitHub stars~897 tokensUpdated 1 mo ago
    SecurityAuto-check passed

More from EpicenterHQ/epicenter

All 65 skills in this repo
  • Agent Instructions

    EpicenterHQ/epicenter

    Write and maintain repository guidance across AGENTS.md, CLAUDE.md, and .agents/skills.

    4.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Consult Claude

    EpicenterHQ/epicenter

    Assign Claude Code a read-only investigation, recommendation, or finished text draft.

    4.8k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Better Auth security hardening: rate limits, secrets, CSRF, trusted origins, cookies, sessions, OAuth tokens, and audit logging.

    4.8k GitHub stars~896 tokensUpdated today
    Auto-check passed
  • Cohesion Over Testability

    EpicenterHQ/epicenter

    Collapse test-shaped production boundaries while preserving behavior and coverage.

    4.8k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Collapse Pass

    EpicenterHQ/epicenter

    Remove indirection that does not earn its boundary across a diff or package.

    4.8k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Error Handling

    EpicenterHQ/epicenter

    Apply Wellcrafted Result patterns to fallible operations and preserve failures at boundaries.

    4.8k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Questions about Code Prose

What does Code Prose do?

Apply Orwell's rules to the prose inside code — identifiers and comments — without changing behavior. Code Prose is an agent skill from EpicenterHQ/epicenter. Apply Orwell's rules to the prose inside code — identifiers and comments — without changing behavior.

When should I use Code Prose?

Code Prose fits situations like: comments need an editorial pass.

How do I install Code Prose in Claude Code?

Run `npx skills add EpicenterHQ/epicenter --skill code-prose -a claude-code`. Or copy the skill folder (.agents/skills/code-prose in EpicenterHQ/epicenter) into .claude/skills/code-prose in your project. Claude Code loads it when a task matches its description.

How do I install Code Prose in Codex?

Run `npx skills add EpicenterHQ/epicenter --skill code-prose -a codex`. Or copy the skill folder (.agents/skills/code-prose in EpicenterHQ/epicenter) into .agents/skills/code-prose in your project. Codex loads it when a task matches its description.

Can I use Code Prose 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 EpicenterHQ/epicenter --skill code-prose -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-prose, .gemini/skills/code-prose, .github/skills/code-prose and .opencode/skills/code-prose in your project.

What does Code Prose need to run?

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

Does Code Prose 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 Code Prose 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 Code Prose use?

Code Prose has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Code Prose use?

About 607 tokens (SKILL.md is roughly 2.4k 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 Code Prose?

Skills that share tags, products or a category with Code Prose: Prose (static-web-server/static-web-server, 2.4k stars), Beautiful Prose (sickn33/agentic-awesome-skills, 47k stars), Identify (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars) and Identify Assumptions Existing (phuryn/pm-skills, 27k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Prose?

EpicenterHQ (a GitHub organization) maintains it in EpicenterHQ/epicenter, which has 4,819 GitHub stars. The repository holds 65 skills in this directory. The repository was last updated on October 8, 2026.

Source: EpicenterHQ/epicenter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.