agentmods.dev

workspace-config

workspace-config is a skill for Claude Code, Codex from ithinkihaveacat/dotfiles. It costs 78 tokens per session (3,341 once invoked), scanned C, original, Apache-2.0.

A workspace setup tool for coding agents. It manages agent skills, tool permissions, Git hooks, and .envrc environment configurations without adding that setup to version control.

In plain words
What is it for?
Use it to install skills as untracked links, set allow/deny/ask rules for agents, manage Git hook profiles, and configure workspace environment files.
Why use it?
It keeps agent-related configuration consistent while keeping it out of the files Git tracks. It can also apply setup automatically after cloning a Git repository.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code.

not rated 48repo changed 3d ago C scan 78 tokens original Apache-2.0

Good fit Use it to install skills as untracked links, set allow/deny/ask rules for agents, manage Git hook profiles, and configure workspace environment files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ithinkihaveacat/dotfiles/workspace-config
View source ↗ ithinkihaveacat/dotfiles
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 ithinkihaveacat/dotfiles --skill workspace-config
Clone the repo
git clone --depth 1 https://github.com/ithinkihaveacat/dotfiles

Made for: Claude Code, Codex.

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 workspace-config

README.md
[![agentmods](https://agentmods.dev/badge/skills/ithinkihaveacat/dotfiles/workspace-config.svg)](https://agentmods.dev/skills/ithinkihaveacat/dotfiles/workspace-config)
Your own site
<a href="https://agentmods.dev/skills/ithinkihaveacat/dotfiles/workspace-config"><img src="https://agentmods.dev/badge/skills/ithinkihaveacat/dotfiles/workspace-config.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,341 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00078 $0.03341
Opus 5 $0.00039 $0.01670
Sonnet 5 $0.00016 $0.00668
Haiku 4.5 $0.00008 $0.00334

Measured 3d ago against content hash 4080af6f3689, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

workspace-config scanned grade C with 1 finding 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (tests/common.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

permission add --deny "rm -rf" # block outright
skills/workspace-config/SKILL.md · 331 lines

How it starts

The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workspace Configuration

This skill configures a workspace for agent-assisted development without version control ever seeing the configuration. It consists of three tools:

  1. hook: The git hook manager. Synchronizes git hooks to match AGENT_REQUIRED_HOOKS (profiles agent, node, gerrit), managing them via trampoline stubs in .git/hooks/.
  2. skill: The workspace manager. Installs and tracks skills as untracked symlinks, automatically adapting to the environment (Git, Perforce, or unmanaged directories; more via plugins). Also provides advisory LLM-based skill recommendations (skill suggest) and manages remote plugin caching.
  3. permission: The permission manager. Maintains allow/deny/ask rules for every detected local agent (workspace-local for Claude Code, user-wide for Antigravity), including pre-approving the safe commands declared by installed skills.

For Git repositories, hook apply, skill apply, and permission apply run automatically on git clone via the global template's post-checkout hook.

Managing Skills (skill)

The skill tool (symlinked in bin/) manages agent skills as untracked symlinks in your workspace. It automatically detects your environment and applies the correct tracking and ignoring mechanism.

skill <command> [arguments]

Supported Environments

  • Git Repositories: Links skills under .agents/skills/ and .claude/skills/. A marker block in .git/info/exclude is dynamically generated to keep git status clean without dirtying the shared .gitignore. If another tool rewrites the exclude file, skill doctor detects the drift, and running skill apply resolves it.
  • Unmanaged Directories: Works in plain directories without VCS, symlinking skills under local destination folders.
  • Plugins: Additional workspace types can be registered by dropping a Python file into ~/.config/skill/plugins/ that defines register(api) and calls api.register_workspace(cls) with a subclass of api.Workspace (see also api.FileStateMixin) implementing a detect() classmethod. Plugin detectors run before the built-in ones, in sorted filename order.

Read the full file on GitHub · 331 lines

Files

What ships with it

16 files 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. 3d ago Changed · +11 lines 4080af6f3689
  2. 8d ago First seen · 320 lines · 78 tokens per session scan C 4624996449b8

Subscribe to this mod's changes

workspace-config is a skill published in the GitHub repository ithinkihaveacat/dotfiles (48 stars, last pushed today), licensed Apache-2.0. It adds 78 tokens to every session and 3,341 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agentsGit and workflowdotfilesfishshell
Related

Other skills, from other repositories

mbo-plan

Plan a new objective end-to-end in this repo's docs/mbo Management-By-Objective system — turn a GitHub issue or a gss draft-PR worktree into consistent design/spec/plan artifacts and track it in docs/mbo/index.md. Use this whenever the user wants to START planning or designing a new feature, skill, CLI, or service…

sfc-gh-eraigosa/dotfiles · 260 tokens

wispr-flow-debug

Debug and test the Wispr Flow AutoHotkey dictation triggers (Copilot key + extra keys) from WSL by deploying macos.ahk to the Windows Desktop, reloading AutoHotkey, and reading the debug log. Use when an activation/trigger key isn't starting/stopping dictation, when the overlay clicks land wrong, or when verifying a…

sfc-gh-eraigosa/dotfiles · 87 tokens

herdr

Use when the user mentions herdr or is working inside a herdr pane and wants to save/restore a pane layout, change herdr's theme, prefix or other preferences on this host only, start or check on an agent in another herdr pane, or asks why the herdr sidebar colors are unreadable. Requires HERDRENV=1.

sfc-gh-eraigosa/dotfiles · 74 tokens

pr-list

List GitHub Pull Requests in a Discord-friendly format with status icons, blockquotes, and direct links. Use when the user asks for "pr list", "list PRs", "open pull requests", or a chat-ready summary of PRs for a repository.

sfc-gh-eraigosa/dotfiles · 56 tokens

google-docs

Integration for interacting with Google Docs and Google Workspace using the 'gws' CLI.

sfc-gh-eraigosa/dotfiles · 21 tokens

sync-forks

Check how many of your GitHub forks are out of date and sync them.

sfc-gh-eraigosa/dotfiles · 20 tokens