Agent skill

Writers Pattern

by caliber-ai-org in caliber-ai-org/ai-setup

Add a new platform writer module in src/writers/ that generates and writes agent config files for a supported platform.

MITAuto-check passedDevelopment

Install Writers Pattern

skills CLI
$ npx skills add caliber-ai-org/ai-setup --skill writers-pattern -a claude-code

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

GitHub CLI
$ gh skill install caliber-ai-org/ai-setup writers-pattern --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/caliber-ai-org/ai-setup.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/writers-pattern .claude/skills/writers-pattern && 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
writers-pattern
GitHub stars
1.3k
Token cost
~3.7k tokens
SKILL.md length
1,253 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Add a new platform writer module in src/writers/ that generates and writes agent config files for a supported platform.

  • Works in 6 steps: Define the Platform Config Interface → Implement the Writer Export Function → Add Type Exports (if complex interface) → …
  • Adding platform support for a new agent
  • SKILL.md covers Critical, Instructions, Examples and Common Issues
  • Calls npm

What it does

Writers Pattern is an agent skill from caliber-ai-org/ai-setup. Add a new platform writer module in src/writers/ that generates and writes agent config files for a supported platform. Each writer exports a function that accepts a config interface, creates directories (rules/, skills/, mcp configs), writes files with proper formatting and frontmatter, and returns string[] of written file paths. Use when adding platform support for a new agent, integrating a new code AI tool, or extending caliber to support new targets. Do NOT use for modifying existing writers, refactoring…

Its SKILL.md is about 3.7k 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 Development, covering Refactoring. It works with Model Context Protocol. The repository describes itself as: Continuously sync your AI setups with one command. Codebase tailor suited agent skills, MCPs and config files for Claude Code, Cursor, and Codex. The licence is MIT.

When your agent uses it

  • Adding platform support for a new agent
  • Integrating a new code AI tool
  • Extending caliber to support new targets
  • Modifying existing writers

Example prompts

  • “/writers-pattern”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Define the Platform Config Interface
  2. Implement the Writer Export Function
  3. Add Type Exports (if complex interface)
  4. Import and Register in src/writers/index.ts
  5. Add Tests
  6. Update detectSyncedAgents() in src/commands/refresh.ts (Optional)

What it can do on your machine

Read from SKILL.md and the folder at commit f5dbc00. 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

    Shell commands in SKILL.md call:

    • npm

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

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    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

Writers Pattern loads about 3.7k tokens when it runs. Until then it costs about 146 tokens; SKILL.md has 1,253 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~146
When it runs · the whole SKILL.md, loaded when a task matches
~3.7k

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 caliber-ai-org/ai-setup at commit f5dbc00, republished under its MIT licence (© caliber-ai-org). 1,253 words, ~3,727 tokens.

Download SKILL.mdSave it as .claude/skills/writers-pattern/SKILL.md (or your agent's skills folder).
name
writers-pattern
description
Add a new platform writer module in src/writers/ that generates and writes agent config files for a supported platform. Each writer exports a function that accepts a config interface, creates directories (rules/, skills/, mcp configs), writes files with proper formatting and frontmatter, and returns string[] of written file paths. Use when adding platform support for a new agent, integrating a new code AI tool, or extending caliber to support new targets. Do NOT use for modifying existing writers, refactoring scoring logic, or changing how writers are invoked.
paths
src/writers/*/index.ts, src/writers/__tests__/*.test.ts, src/writers/index.ts

Platform Writer Pattern

Critical

  • Every writer MUST:

    1. Export a single named function: write<Platform>Config(config: <PlatformConfig>): string[]
    2. Accept a platform-specific config interface defining what content to write
    3. Return string[] of all written file paths (used by manifest and progress display)
    4. Create parent directories with fs.mkdirSync(dir, { recursive: true }) before writing files
    5. Wrap skill frontmatter exactly as shown in Step 4 (YAML between --- markers)
    6. NOT modify files outside the intended platform directories (e.g., Claude writer only touches .claude/, CLAUDE.md, .mcp.json)
  • Integration point: Every writer MUST be imported and called in src/writers/index.ts within the writeSetup() function. Missing this step means the writer will never execute.

  • Validation before Step 1: Verify the platform name is unique (ls src/writers/ shows no <platform>/index.ts). If it exists, you are modifying, not adding.

Instructions

Step 1: Define the Platform Config Interface

Verify the platform name is unique (see Critical). Create src/writers/<platform>/index.ts.

At the top of the file, define a config interface that describes all content the writer accepts. The interface MUST include:

  • A main markdown/text file (e.g., claudeMd, cursorrules, agentsMd, instructions)
  • Optional nested arrays: rules, skills, mcpServers, instructionFiles, etc.
  • Each rule/skill/file has at minimum: name or filename, content, and for skills, description

Example (matching GitHub Copilot pattern already in codebase):

typescript
interface CopilotConfig {
  instructions: string;  // Main content
  instructionFiles?: Array<{ filename: string; content: string }>;
}

Validation: Confirm the interface property names match platform conventions (e.g., Claude uses claudeMd, Cursor uses cursorrules). Check existing writers: src/writers/claude/index.ts line 9, src/writers/cursor/index.ts line 9, src/writers/codex/index.ts line 5.

Step 2: Implement the Writer Export Function

Export a function named write<Platform>Config(config: <PlatformConfig>): string[] that:

  1. Initialize an empty written: string[] = [] array to track all written paths.

  2. For the main config file (e.g., CLAUDE.md for Claude, .cursorrules for Cursor):

    • Wrap the content with platform-specific blocks: Use helpers from src/writers/pre-commit-block.ts
    • Common blocks: appendPreCommitBlock(content, platform), appendLearningsBlock(content), appendSyncBlock(content)
    • Examples from actual codebase:
      • Claude (src/writers/claude/index.ts line 19-22): appendSyncBlock(appendLearningsBlock(appendPreCommitBlock(config.claudeMd)))
      • Cursor (src/writers/cursor/index.ts line 19-22): No sync block; injects rules instead (pre-commit, learnings, sync as separate files)
      • Codex (src/writers/codex/index.ts line 13-16): appendLearningsBlock(appendPreCommitBlock(config.agentsMd, 'codex'))
      • Copilot (src/writers/github-copilot/index.ts line 19-22): appendSyncBlock(appendLearningsBlock(appendPreCommitBlock(config.instructions, 'copilot')))
    • Write to the exact path (e.g., fs.writeFileSync('CLAUDE.md', wrappedContent)) and push to written.
  3. For rules (if applicable): Platform convention determines directory.

    • Cursor uses .cursor/rules/, Claude uses .claude/rules/ (see src/writers/index.ts lines 123-126 and 135-137)
    • For each rule: create the directory, write to <dir>/<rule.filename>, push path to written
    • Cursor special case (src/writers/cursor/index.ts line 24-27): Cursor injects three system rules:
      typescript
      const preCommitRule = getCursorPreCommitRule();
      const learningsRule = getCursorLearningsRule();
      const syncRule = getCursorSyncRule();
      const allRules = [...(config.rules || []), preCommitRule, learningsRule, syncRule];
  4. For skills: Write with YAML frontmatter.

    • Directory pattern: .claude/skills/<skillName>/SKILL.md, .cursor/skills/<skillName>/SKILL.md, .agents/skills/<skillName>/SKILL.md, .opencode/skills/<skillName>/SKILL.md
    • Frontmatter format (exact indentation from src/writers/claude/index.ts line 40-47):
      ---
      name: <skill.name>
      description: <skill.description>
      paths:
        - <optional path pattern 1>
        - <optional path pattern 2>
      ---
      <skill.content>
    • For Opencode (src/writers/opencode/index.ts line 30): Use buildSkillContent(skill) from src/lib/builtin-skills.js instead of manual frontmatter.
    • Create directory with fs.mkdirSync(skillDir, { recursive: true }), write skill, push to written
  5. For MCP Servers (if applicable): Write/merge JSON at platform-specific path.

    • Claude (src/writers/claude/index.ts line 54-65): .mcp.json at root
    • Cursor (src/writers/cursor/index.ts line 54-69): .cursor/mcp.json
    • Pattern: Read existing servers (if file exists, try to parse JSON with try/catch), merge with new servers using spread operator { ...existingServers, ...config.mcpServers }, write merged object
    • Wrap in { mcpServers: mergedServers } and output as pretty-printed JSON: JSON.stringify(wrapped, null, 2)
  6. For instruction files (GitHub Copilot, src/writers/github-copilot/index.ts line 26-33): Write to .github/instructions/ directory.

    • Create directory, iterate files, write each to <dir>/<file.filename>, push paths

Return the written array.

Validation: Confirm all file write operations are synchronous (fs.writeFileSync, fs.mkdirSync). Ensure every written path is added to the array. No async operations allowed.

Step 3: Add Type Exports (if complex interface)

If the config interface may be reused elsewhere (e.g., in src/writers/index.ts for the AgentSetup type), export the interface from the module.

Validation: Check src/writers/index.ts lines 15-19 to see if new agent setup params are needed.

Step 4: Import and Register in src/writers/index.ts

Open src/writers/index.ts. At the top (around line 2-6), add:

typescript
import { write<Platform>Config } from './<platform>/index.js';

Update the AgentSetup interface (around line 12-20):

  • Add '<platform>' to the targetAgent tuple (line 13: ('claude' | 'cursor' | 'codex' | 'opencode' | 'github-copilot' | '<platform>')[])
  • Add a new property: <platform>?: Parameters<typeof write<Platform>Config>[0];

Update getFilesToWrite() function (starting line 117): Add a new conditional block:

typescript
if (setup.targetAgent.includes('<platform>') && setup.<platform>) {
  files.push('<main-config-file>');
  if (setup.<platform>.rules) {
    for (const r of setup.<platform>.rules) files.push(`<rules-dir>/${r.filename}`);
  }
  if (setup.<platform>.skills) {
    for (const s of setup.<platform>.skills) files.push(`<skills-dir>/${s.name}/SKILL.md`);
  }
  // ... repeat for other config types (mcpServers, instructionFiles, etc.)
}

Update writeSetup() function (starting line 22): Add a new conditional block before the return (after line 56):

typescript
if (setup.targetAgent.includes('<platform>') && setup.<platform>) {
  written.push(...write<Platform>Config(setup.<platform>));
}

Validation: Confirm the function call order in writeSetup() is consistent (line 37-56): claude → cursor → codex → opencode → github-copilot → (new platform). This ensures AGENTS.md is written once if shared (as with Codex/Opencode, see line 50-52).

Step 5: Add Tests

Create src/writers/__tests__/<platform>.test.ts following the vitest pattern in src/writers/__tests__/codex.test.ts:

  1. Mock fs module: vi.mock('fs')
  2. Mock return values in beforeEach: vi.mocked(fs.existsSync).mockReturnValue(false)
  3. Test that:
    • Main config file is written to correct path
    • Returned array includes all written paths
    • Directories are created before file writes (use .toHaveBeenCalledWith(path, { recursive: true }))
    • Skills have correct frontmatter format (check vi.mocked(fs.writeFileSync).mock.calls)
    • MCP/instruction files are merged/created correctly
    • Pre-commit/learnings/sync blocks are included in main file (expect content .toContain('caliber:managed:pre-commit'))

Run: npm test -- src/writers/__tests__/<platform>.test.ts

Validation: All tests pass. Confirm mocked file operations match actual file system structure.

Show full SKILL.md (559 more words)Show less
Step 6: Update detectSyncedAgents() in src/commands/refresh.ts (Optional)

If the platform writes config files with distinct naming (e.g., .newplatform/), update the detection logic around line 68-77 so end-user refresh output correctly identifies the synced platform:

typescript
if (joined.includes('.newplatform/') || joined.includes('newplatform-config')) {
  agents.push('<Platform Name>');
}

Validation: Run npm run refresh and confirm the summary message lists the new platform.

Examples

Example 1: Add a hypothetical "DevCode" platform writer

User says: "Add support for DevCode, a new agent that reads config from .devcode/settings.md and .devcode/rules/ directory."

Actions taken:

  1. Create src/writers/devcode/index.ts (matching pattern from src/writers/claude/index.ts):

    typescript
    import fs from 'fs';
    import path from 'path';
    import { appendPreCommitBlock, appendLearningsBlock } from '../pre-commit-block.js';
    
    interface DevcodeConfig {
      settingsMd: string;
      rules?: Array<{ filename: string; content: string }>;
    }
    
    export function writeDevcodeConfig(config: DevcodeConfig): string[] {
      const written: string[] = [];
    
      fs.writeFileSync(
        '.devcode/settings.md',
        appendLearningsBlock(appendPreCommitBlock(config.settingsMd, 'devcode'))
      );
      written.push('.devcode/settings.md');
    
      if (config.rules?.length) {
        const rulesDir = path.join('.devcode', 'rules');
        if (!fs.existsSync(rulesDir)) fs.mkdirSync(rulesDir, { recursive: true });
        for (const rule of config.rules) {
          const rulePath = path.join(rulesDir, rule.filename);
          fs.writeFileSync(rulePath, rule.content);
          written.push(rulePath);
        }
      }
    
      return written;
    }
  2. Update src/writers/index.ts:

    • Line 2: Add import { writeDevcodeConfig } from './devcode/index.js';
    • Line 13: Change targetAgent tuple to include 'devcode'
    • Line 19: Add devcode?: Parameters<typeof writeDevcodeConfig>[0];
    • Line 117+: Add devcode block to getFilesToWrite() (match Codex pattern lines 144-149)
    • Line 37+: Add devcode block to writeSetup() (match Codex pattern lines 45-47)
    • Line 68+: Update detectSyncedAgents() to check for .devcode/
  3. Create src/writers/__tests__/devcode.test.ts (matching src/writers/__tests__/codex.test.ts):

    typescript
    import { describe, it, expect, vi, beforeEach } from 'vitest';
    import fs from 'fs';
    import path from 'path';
    
    vi.mock('fs');
    
    import { writeDevcodeConfig } from '../devcode/index.js';
    
    describe('writeDevcodeConfig', () => {
      beforeEach(() => {
        vi.clearAllMocks();
        vi.mocked(fs.existsSync).mockReturnValue(false);
      });
    
      it('writes settings.md and rules', () => {
        const config = {
          settingsMd: '# DevCode Config',
          rules: [{ filename: 'style.md', content: 'Style rules' }],
        };
        const written = writeDevcodeConfig(config);
        expect(written).toContain('.devcode/settings.md');
        expect(written).toContain(path.join('.devcode', 'rules', 'style.md'));
      });
    });
  4. Run: npm test && npm run build

Result: Caliber now generates .devcode/settings.md and rules on caliber refresh and caliber init.

Common Issues

Issue: "TypeError: write<Platform>Config is not a function"

  • Fix: Verify the function is exported (not just defined). Check export function write<Platform>Config(...) in the writer file. Missing export is a common mistake.

Issue: "ENOENT: no such file or directory, open '.platform/config.md'"

  • Fix: The parent directory was not created. Ensure fs.mkdirSync(parentDir, { recursive: true }) is called before fs.writeFileSync(filePath, content). See correct order in src/writers/claude/index.ts lines 26-27.

Issue: "Skill file has no frontmatter / malformed YAML"

  • Fix: Verify frontmatter format is exactly (no extra blank lines):
    ---\nname: <name>\ndescription: <desc>\n---\n<content>
    Use [...].join('\n') and test with a single skill first. Compare with working code in src/writers/claude/index.ts lines 40-48.

Issue: "MCP servers not merging, file is truncated"

  • Fix: Confirm the merge pattern from src/writers/claude/index.ts line 54-65: read existing JSON (with try/catch), parse safely, merge with spread operator { ...existingServers, ...config.mcpServers }, then write the merged object. Do NOT overwrite — always merge.

Issue: "new writer is called but written files are empty array"

  • Fix: Verify the writer function returns the written array. Check that every file operation pushes to written. Missing a written.push(filePath) after fs.writeFileSync() is the most common error. See src/writers/codex/index.ts lines 17 and 32 for correct pattern.

Issue: "Tests mock fs but actual files are created in .tmp/ or cause permission errors"

  • Fix: Ensure vi.mock('fs') is at the top of the test file before any imports. All fs operations will be mocked and return mock values from beforeEach setup. See src/writers/__tests__/codex.test.ts line 5.

Issue: "Cursor pre-commit rule not applied, or learnings block missing"

  • Fix: Cursor injects system rules during the write, unlike Claude which uses block appenders. Check that getCursorPreCommitRule(), getCursorLearningsRule(), and getCursorSyncRule() are called and concatenated with user rules before iterating (see src/writers/cursor/index.ts lines 24-27). Claude and Codex use block-append helpers instead.

© caliber-ai-org, 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 skills/writers-pattern of caliber-ai-org/ai-setup.

Open the folder on GitHubat commit f5dbc00

Compare with similar skills

Writers Pattern 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.

Writers Pattern compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Writers Pattern this skillcaliber-ai-org/ai-setup1.3k—~3.7kAutomated safety check: PassMIT
Filescope MCPadmica/FileScopeMCP302—~1.7kAutomated safety check: PassProprietary
Gograph Go Repository Intelligenceozgurcd/gograph228—~4.8kAutomated safety check: NotesMIT
Memtrace Decision Memorysyncable-dev/memtrace-public489—~1.9kAutomated safety check: PassCustom licence
Testing With API Mocksstacklok/toolhive-studio170—~1.5kAutomated safety check: PassApache-2.0
Edt MCP Project Local FixDitriXNew/EDT-MCP295—~507Automated safety check: PassAGPL-3.0

Similar skills

  • Filescope MCP

    admica/FileScopeMCP

    Codebase intelligence via FileScopeMCP — symbol lookup, dependency mapping, importance ranking, and semantic search.

    302 GitHub stars~1.7k tokensUpdated 5 mo ago
    DevelopmentAuto-check passed
  • Gives an agent working in a Go codebase a structural view through a local MCP server: call graphs, blast-radius and impact analysis, and bounded first-call exploration.

    228 GitHub stars~4.8k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Memtrace Decision Memory

    syncable-dev/memtrace-public

    Use Cortex decision memory through the normal Memtrace MCP tools.

    489 GitHub stars~1.9k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Testing With API Mocks

    stacklok/toolhive-studio

    Start here for all API mocking in tests. An agent skill from stacklok/toolhive-studio.

    170 GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Edt MCP Project Local Fix

    DitriXNew/EDT-MCP

    Apply one bounded BSL correction through EDT-MCP with lost-update protection, targeted validation, and minimal diff.

    295 GitHub stars~507 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • ast-grep Structural Search

    code-yeongyu/oh-my-openagent

    Searches and rewrites code by syntax-tree shape across 25 languages with ast-grep, for codemods, structural queries and YAML lint rules, using a Python wrapper script.

    70k GitHub stars~3.3k tokensUpdated today
    DevelopmentAuto-check passed

More from caliber-ai-org/ai-setup

All 8 skills in this repo
  • Adding A Command

    caliber-ai-org/ai-setup

    Creates a new CLI command following the Commander.js pattern in src/commands/.

    1.3k GitHub stars~2k tokensUpdated 15 days ago
    Auto-check passed
  • Caliber Testing

    caliber-ai-org/ai-setup

    Writes Vitest tests following project patterns: tests/ directories, vi.mock() for module mocking with vi.hoisted() for test-time factories, global LLM mock from src/test/setup.ts, environment…

    1.3k GitHub stars~3.2k tokensUpdated 15 days ago
    Auto-check passed
  • Find Skills

    caliber-ai-org/ai-setup

    Discovers and installs community skills from the public registry.

    1.3k GitHub stars~593 tokensUpdated 15 days ago
    Auto-check passed
  • LLM Provider

    caliber-ai-org/ai-setup

    Adds a new LLM provider implementing LLMProvider interface with call() and stream() methods.

    1.3k GitHub stars~2.7k tokensUpdated 15 days ago
    Auto-check passed
  • Save Learning

    caliber-ai-org/ai-setup

    Saves user instructions as persistent learnings for future sessions.

    1.3k GitHub stars~626 tokensUpdated 15 days ago
    Auto-check passed
  • Scoring Checks

    caliber-ai-org/ai-setup

    Add a new deterministic scoring check in src/scoring/checks/ that evaluates config quality.

    1.3k GitHub stars~3k tokensUpdated 15 days ago
    Auto-check passed

Questions about Writers Pattern

What does Writers Pattern do?

Add a new platform writer module in src/writers/ that generates and writes agent config files for a supported platform. Writers Pattern is an agent skill from caliber-ai-org/ai-setup. Add a new platform writer module in src/writers/ that generates and writes agent config files for a supported platform.

When should I use Writers Pattern?

Writers Pattern fits situations like: adding platform support for a new agent; integrating a new code AI tool; extending caliber to support new targets; modifying existing writers.

How do I install Writers Pattern in Claude Code?

Run `npx skills add caliber-ai-org/ai-setup --skill writers-pattern -a claude-code`. Or copy the skill folder (skills/writers-pattern in caliber-ai-org/ai-setup) into .claude/skills/writers-pattern in your project. Claude Code loads it when a task matches its description.

How do I install Writers Pattern in Codex?

Run `npx skills add caliber-ai-org/ai-setup --skill writers-pattern -a codex`. Or copy the skill folder (skills/writers-pattern in caliber-ai-org/ai-setup) into .agents/skills/writers-pattern in your project. Codex loads it when a task matches its description.

Can I use Writers Pattern 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 caliber-ai-org/ai-setup --skill writers-pattern -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writers-pattern, .gemini/skills/writers-pattern, .github/skills/writers-pattern and .opencode/skills/writers-pattern in your project.

What does Writers Pattern need to run?

Going by SKILL.md and its folder, Writers Pattern needs the command-line tools its instructions call (npm).

Does Writers Pattern access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Writers Pattern 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 Writers Pattern use?

Writers Pattern is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Writers Pattern use?

About 3.7k tokens (SKILL.md is roughly 15k 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 Writers Pattern?

Skills that share tags, products or a category with Writers Pattern: Filescope MCP (admica/FileScopeMCP, 302 stars), Gograph Go Repository Intelligence (ozgurcd/gograph, 228 stars), Memtrace Decision Memory (syncable-dev/memtrace-public, 489 stars) and Testing With API Mocks (stacklok/toolhive-studio, 170 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Writers Pattern?

caliber-ai-org (a GitHub organization) maintains it in caliber-ai-org/ai-setup, which has 1,301 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 24, 2026.

Source: caliber-ai-org/ai-setup on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.