New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Mic

by Spearmintai in Spearmintai/mintocode

A skill your agent uses when working in a repository that has a .micode/ directory (a compiled understanding of the codebase) — to answer questions about the code, locate where something is…

MITAuto-check passed

Install Mic

skills CLI
$ npx skills add Spearmintai/mintocode --skill mic -a claude-code

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

GitHub CLI
$ gh skill install Spearmintai/mintocode mic --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/Spearmintai/mintocode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mic .claude/skills/mic && 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
mic
GitHub stars
393
Token cost
~563 tokens
SKILL.md length
261 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when working in a repository that has a .micode/ directory (a compiled understanding of the codebase) — to answer questions about the code, locate where something is…

  • Works in 4 steps: Check the block injected with the user's… → Otherwise call the mic MCP tools before… → Read only the cited spans (Read with… → …
  • Working in a repository that has a .micode/ directory (a compiled understanding of the codebase) — to answer questions about the code
  • SKILL.md covers Order of operations, Pure questions and Maintenance
  • Calls python3

What it does

Mic is an agent skill from Spearmintai/mintocode. Use when working in a repository that has a .micode/ directory (a compiled understanding of the codebase) — to answer questions about the code, locate where something is implemented, plan a change, or find what calls what, with far fewer tokens than exploring with Grep/Glob/Read. Also use when the user asks to compile, update or check the compiled understanding.

Its SKILL.md is about 560 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is MIT.

When your agent uses it

  • Working in a repository that has a .micode/ directory (a compiled understanding of the codebase) — to answer questions about the code
  • Locate where something is implemented
  • Find what calls what
  • With far fewer tokens than exploring with Grep/Glob/Read

Example prompts

  • “/mic”

Requirements

  • Python 3

Workflow steps

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

  1. Check the block injected with the user's prompt: the minimal linked paragraphs for it (the
  2. Otherwise call the mic MCP tools before exploring
  3. Read only the cited spans (Read with offset/limit). Use Grep only for what the compile cannot know, such as
  4. Before editing, read the exact lines you change. Items marked ⚠stale changed after the compile.

What it can do on your machine

Read from SKILL.md and the folder at commit e2d14c4. 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:

    • python3

    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

Mic loads about 563 tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 261 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~563

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 Spearmintai/mintocode at commit e2d14c4, republished under its MIT licence (© Spearmintai). 261 words, ~563 tokens.

Download SKILL.mdSave it as .claude/skills/mic/SKILL.md (or your agent's skills folder).
name
mic
description
Use when working in a repository that has a .micode/ directory (a compiled understanding of the codebase) — to answer questions about the code, locate where something is implemented, plan a change, or find what calls what, with far fewer tokens than exploring with Grep/Glob/Read. Also use when the user asks to compile, update or check the compiled understanding.

Working from a compiled repository

.micode/ holds a compile of this repository made by a strong model: a core card (already in context at session start), module cards, file cards, a precompiled bank of question/answer pairs, end-to-end flows, and a deterministic symbol table. Every path:Lstart-end citation in it was checked against the source.

Order of operations

  1. Check the <micode-context> block injected with the user's prompt: the minimal linked paragraphs for it (the best-matching functions with their source, plus the definitions they use, their callers and tests). If it answers the question, answer from it and cite its spans.
  2. Otherwise call the mic MCP tools before exploring:
    • ask(question) — precompiled answers plus the relevant files with exact spans
    • where(symbol) — definition sites
    • card(path) — a file's full map (purpose, every symbol with its span, facts, gotchas)
    • module(path) — responsibilities, interfaces, how-to recipes of a directory
    • deps(path) — what a file imports and what imports it (blast radius) Without MCP, the same commands exist as python3 "${CLAUDE_PLUGIN_ROOT}/bin/mic" ask|where|card ....
  3. Read only the cited spans (Read with offset/limit). Use Grep only for what the compile cannot know, such as runtime strings or new code.
  4. Before editing, read the exact lines you change. Items marked ⚠stale changed after the compile.

Pure questions

For a question that needs no edit, /mic:ask <question> answers from the linked paragraphs in one cheap model call, without an exploration loop.

Maintenance

  • /mic:compile makes the first compile, /mic:update recompiles changed files incrementally, and /mic:status shows staleness and cost.
  • Commit .micode/ (its own .gitignore excludes the cache) so the whole team reuses one compile.

© Spearmintai, 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/mic of Spearmintai/mintocode.

Open the folder on GitHubat commit e2d14c4

Compare with similar skills

Mic 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.

Mic compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mic this skillSpearmintai/mintocode393—~563Automated safety check: PassMIT
Directory Submissionscoreyhaines31/marketingskills54k2 repos~6.7kAutomated safety check: PassMIT
Brilliant Directories AutomationComposioHQ/awesome-claude-skills77k3 repos~783Automated safety check: PassNone
SEO Directory Backlinkssickn33/agentic-awesome-skills47k1 repos~6.5kAutomated safety check: PassMIT
People Directorysickn33/agentic-awesome-skills47k1 repos~4.5kAutomated safety check: PassMIT
Deploying Active Directory Honeytokensmukul975/Anthropic-Cybersecurity-Skills34k—~2.4kAutomated safety check: PassApache-2.0

Similar skills

  • Directory Submissions

    coreyhaines31/marketingskills

    When the user wants to submit their product to startup, SaaS, AI, agent, MCP, no-code, or review directories for backlinks, domain rating, and discovery.

    54k GitHub starsUsed in 2 repos~6.7k tokens
    Marketing & SEOAuto-check passed

  • Brilliant Directories Automation

    ComposioHQ/awesome-claude-skills

    Automate Brilliant Directories tasks via Rube MCP (Composio).

    77k GitHub starsUsed in 3 repos~783 tokens
    Productivity & AutomationAuto-check passed

  • SEO Directory Backlinks

    sickn33/agentic-awesome-skills

    Directory and backlink register: platform, domain, target URL, follow attribute, authority and spam scores, approval and NAP-match status.

    47k GitHub starsUsed in 1 repo~6.5k tokens
    Marketing & SEOAuto-check passed

  • People Directory

    sickn33/agentic-awesome-skills

    Employee master record: name, employee id, department, job title, grade, manager, employment type, contact and emergency details, access role, start and end dates, status.

    47k GitHub starsUsed in 1 repo~4.5k tokens
    Auto-check passed

  • Deploying Active Directory Honeytokens

    mukul975/Anthropic-Cybersecurity-Skills

    Deploys deception-based honeytokens in Active Directory including fake privileged accounts with AdminCount=1, fake SPNs for Kerberoasting detection (honeyroasting), decoy GPOs with cpassword traps…

    34k GitHub stars~2.4k tokensUpdated 1 mo ago
    SecurityAuto-check passed

  • Analyzing Active Directory Acl Abuse

    mukul975/Anthropic-Cybersecurity-Skills

    Detect dangerous ACL misconfigurations in Active Directory using ldap3 to identify GenericAll, WriteDACL, and WriteOwner abuse paths

    34k GitHub stars~1.1k tokensUpdated 1 mo ago
    SecurityAuto-check passed

Questions about Mic

What does Mic do?

A skill your agent uses when working in a repository that has a .micode/ directory (a compiled understanding of the codebase) — to answer questions about the code, locate where something is…. Mic is an agent skill from Spearmintai/mintocode.micode/ directory (a compiled understanding of the codebase) — to answer questions about the code, locate where something is implemented, plan a change, or find what calls what, with far fewer tokens than exploring with Grep/Glob/Read.

When should I use Mic?

Mic fits situations like: working in a repository that has a .micode/ directory (a compiled understanding of the codebase) — to answer questions about the code; locate where something is implemented; find what calls what; with far fewer tokens than exploring with Grep/Glob/Read.

How do I install Mic in Claude Code?

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

How do I install Mic in Codex?

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

Can I use Mic 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 Spearmintai/mintocode --skill mic -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mic, .gemini/skills/mic, .github/skills/mic and .opencode/skills/mic in your project.

What does Mic need to run?

Going by SKILL.md and its folder, Mic needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Mic 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 Mic 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 Mic use?

Mic 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 Mic use?

About 563 tokens (SKILL.md is roughly 2.3k 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 Mic?

Skills that share tags, products or a category with Mic: Directory Submissions (coreyhaines31/marketingskills, 54k stars), Brilliant Directories Automation (ComposioHQ/awesome-claude-skills, 77k stars), SEO Directory Backlinks (sickn33/agentic-awesome-skills, 47k stars) and People Directory (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mic?

Spearmintai (a GitHub user) maintains it in Spearmintai/mintocode, which has 393 GitHub stars. The repository was last updated on October 9, 2026.

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