DevSpace is a self-hosted Model Context Protocol server that lets ChatGPT work with approved projects on a user’s own computer. It enables ChatGPT to inspect and edit files, search code, run terminal commands, and use isolated Git worktrees. The catalogue entries provide agents, a skill, and an instruction for using this local coding workflow.
Borrowing it
Nothing to install: this file belongs to Waishnav/devspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Waishnav/devspace/main/.agents/skills/setup-qa/SKILL.mdgit clone --depth 1 https://github.com/Waishnav/devspaceWrote 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.
[](https://agentmods.dev/skills/waishnav/devspace/setup-qa)<a href="https://agentmods.dev/skills/waishnav/devspace/setup-qa"><img src="https://agentmods.dev/badge/skills/waishnav/devspace/setup-qa/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.
<a href="https://agentmods.dev/skills/waishnav/devspace/setup-qa"><img src="https://agentmods.dev/badge/skills/waishnav/devspace/setup-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.00408 |
| Opus 5.5 | $0.00020 | $0.00163 |
| Sonnet 5.5 | $0.00010 | $0.00082 |
| Haiku 4.5 | $0.00005 | $0.00041 |
Grade A, and why
setup-qa 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 1mo 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.
What it actually says
Set up DevSpace manual QA
Use the current checkout or worktree. DevSpace's repo-local QA state lives in .devspace-dev/ and should be used instead of the user's normal DevSpace state.
Prepare the checkout
If this checkout has not been initialized for QA yet:
pnpm dev:seed
dev:seed forks the user's current DevSpace config, auth, local skills/agents, and SQLite state into this checkout's .devspace-dev/ directory.
For ChatGPT app, widget, CSS, or icon changes, build the UI assets before testing:
pnpm build:app
The source server serves UI assets from dist/ui, not directly from src/ui.
Run QA
Start the source server from this checkout with:
pnpm dev
It uses .devspace-dev/config and runs the source server under tsx watch, so server-side TypeScript changes reload automatically. Frontend changes still need another pnpm build:app.
The seeded QA state usually lets ChatGPT keep using the existing connector and tunnel while switching from the installed DevSpace server to this checkout's server.
For UI work, trigger a fresh tool result after rebuilding so ChatGPT loads the new hashed Vite assets.
Reset the QA snapshot
Only when a fresh fork of the normal DevSpace state is needed:
pnpm dev:reset
Run this with pnpm dev stopped, then start pnpm dev again so the replaced snapshot is loaded. If the user's normal installation uses a custom DEVSPACE_CONFIG_DIR, preserve it while running dev:seed or dev:reset.
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.
- 1mo ago First seen · 51 lines · 49 tokens per session scan A 15ee886f0eb8
setup-qa is a skill published in the GitHub repository Waishnav/devspace (5,296 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 408 once invoked, about $0.0002 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 2026-09-08.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
verify
Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches…
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
darwinian-evolver
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.