agentmods.dev

local-project-workspace

local-project-workspace is a skill for Claude Code, Codex from dxawdc/chatgpt-workspace-mcp. It costs 35 tokens per session (365 once invoked), scanned A, original, MIT.

A set of instructions for safely using ChatGPT Workspace to work on approved Git and non-Git projects.

In plain words
What is it for?
Use it when discovering projects, reading or changing files, testing work, checking diffs, or delivering authorized Git changes.
Why use it?
It defines how to inspect files, make controlled edits, run allowed tasks, and handle commits and pushes safely.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 0repo 8d ago A scan 35 tokens original MIT

Good fit Use it when discovering projects, reading or changing files, testing work, checking diffs, or delivering authorized Git changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dxawdc/chatgpt-workspace-mcp/local-project-workspace
View source ↗ dxawdc/chatgpt-workspace-mcp
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 dxawdc/chatgpt-workspace-mcp --skill local-project-workspace
Clone the repo
git clone --depth 1 https://github.com/dxawdc/chatgpt-workspace-mcp

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 local-project-workspace

README.md
[![agentmods](https://agentmods.dev/badge/skills/dxawdc/chatgpt-workspace-mcp/local-project-workspace/github.svg)](https://agentmods.dev/skills/dxawdc/chatgpt-workspace-mcp/local-project-workspace)
Your own site
<a href="https://agentmods.dev/skills/dxawdc/chatgpt-workspace-mcp/local-project-workspace"><img src="https://agentmods.dev/badge/skills/dxawdc/chatgpt-workspace-mcp/local-project-workspace/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for local-project-workspace

Your own site · 80×15
<a href="https://agentmods.dev/skills/dxawdc/chatgpt-workspace-mcp/local-project-workspace"><img src="https://agentmods.dev/badge/skills/dxawdc/chatgpt-workspace-mcp/local-project-workspace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 365 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00035 $0.00365
Opus 5.5 $0.00014 $0.00146
Sonnet 5.5 $0.00007 $0.00073
Haiku 4.5 $0.00003 $0.00036

Measured 2mo ago against content hash 82082ff55efc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

local-project-workspace scanned grade A with 0 findings 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 2mo ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/local-project-workspace/SKILL.md · 21 lines

What it actually says

ChatGPT Workspace MCP

Use the MCP tools to work only with project IDs returned by list_projects.

Workflow

  1. Call diagnostics, then list_projects. If the requested project is not authorized, call discover_projects; connect it only when it is beneath a locally approved discovery root. Non-Git projects are supported with commit and push forced off.
  2. Use list_files, search_text, and read_file to inspect the smallest relevant scope.
  3. Before editing an existing file, call read_file again and pass its current sha256 to apply_patch. Use create_text_file only for a new path.
  4. Preserve unrelated changes. After writing to a Git project, call git_diff and git_status. For a non-Git project, do not call Git tools; instead report the explicit files changed.
  5. Run only task names returned for that project. Report the exact task and exit code.
  6. Commit only when the user requests it, projectType is git, and the project reports allowCommit: true. Pass only explicit relative paths and the latest statusSha256 to git_commit. Never mix unrelated or pre-staged changes.
  7. Treat commit and push as separate states. Call git_push only when the user explicitly requests a push and the project reports allowPush: true.

The server deliberately provides no arbitrary shell, force-push, history rewrite, broad staging, or deployment tool. Never imply that a commit or push occurred unless the corresponding tool succeeded.

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. 2mo ago First seen · 21 lines · 35 tokens per session scan A 82082ff55efc

Subscribe to this mod's changes

local-project-workspace is a skill published in the GitHub repository dxawdc/chatgpt-workspace-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 365 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Git and workflowchatgptcodexdeveloper-toolslocal-filesmcp
Related

Other skills, from other repositories

publish-site

Versioned site deploys to GitHub/Cloudflare/Netlify Pages.

NousResearch/hermes-agent · 19 tokens

codex

Delegate coding to OpenAI Codex CLI (features, PRs).

NousResearch/hermes-agent · 17 tokens

code-review

Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's recipe covers them) at the effort level given first, before any target (low|medium|high|xhigh|max: from few high-confidence findings to many, some uncertain; ultra: deep…

asgeirtj/system_prompts_leaks · 230 tokens

batch

Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.

asgeirtj/system_prompts_leaks · 30 tokens

github

Search and work with the user's GitHub repositories through GitHub's official MCP server.

asgeirtj/system_prompts_leaks · 19 tokens

git

Source-control safety for Git. Two rules apply whether or not you read the body. First, never commit, amend, push, tag, rebase, cherry-pick, revert, or reset --hard unless the user asked for that exact write in this session. An explicit request to create a new commit counts anywhere in the user's own task text, but it…

asgeirtj/system_prompts_leaks · 163 tokens