Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/patleeman/neon-pilot/neon-pilot-parallel-qa)<a href="https://agentmods.dev/skills/patleeman/neon-pilot/neon-pilot-parallel-qa"><img src="https://agentmods.dev/badge/skills/patleeman/neon-pilot/neon-pilot-parallel-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/patleeman/neon-pilot/neon-pilot-parallel-qa"><img src="https://agentmods.dev/badge/skills/patleeman/neon-pilot/neon-pilot-parallel-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 | $0.00054 | $0.01146 |
| Opus 5 | $0.00027 | $0.00573 |
| Sonnet 5 | $0.00011 | $0.00229 |
| Haiku 4.5 | $0.00005 | $0.00115 |
Grade A, and why
neon-pilot-parallel-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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neon Pilot Parallel QA
Use this skill to turn the feature inventory QA process into a parallel discover-and-fix worker pipeline without losing strict evidence quality.
Ground Rules
docs/feature-qa-status.mdis the canonical feature queue.- The parent agent is the only authority that updates
docs/feature-inventory.md,docs/feature-qa-status.md, and any findings queue. - Worker output is evidence and candidate fixes, not completion proof. The parent must validate before changing a row status.
- Workers may fix issues they discover inside their assigned lane, but must keep edits narrowly scoped and must not touch inventory/status docs unless explicitly told.
- Workers must not mutate shared app state, unrelated source, git state, or user data. Use isolated app state and disposable fixtures for live QA.
- Every row with a user-visible path still needs live app-path evidence, full visible-viewport raw-internal scan, practical fixes, regression tests for fixes, rebuild/relaunch when required, and inventory/status updates.
Pipeline
- Parent selects a bounded batch of rows from
docs/feature-qa-status.md. - Parent spawns discover-and-fix workers for non-overlapping rows or feature slices.
- Each worker launches an isolated dev app if live UI QA is needed.
- Each worker discovers issues, fixes practical bugs it has enough context to fix, adds focused regressions, and reruns its isolated live path.
- Workers report findings, fixes, tests/builds, evidence paths, and remaining gaps using the schema below.
- Parent reviews worker diffs/evidence, deduplicates cross-worker findings, runs final validation, and decides whether to accept each fix.
- Parent alone updates
docs/feature-inventory.md,docs/feature-qa-status.md, and any findings queue.
Isolated Dev App
Each live worker needs unique runtime isolation:
export NEON_PILOT_STATE_ROOT="/tmp/neon-pilot-qa/$WORKER_ID/state"
export NEON_PILOT_DAEMON_NAMESPACE="qa-$WORKER_ID"
export NEON_PILOT_DESKTOP_INITIAL_ROUTE="/conversations/new"
mkdir -p "/tmp/neon-pilot-qa/$WORKER_ID/screenshots" "/tmp/neon-pilot-qa/$WORKER_ID/logs"
node packages/desktop/scripts/launch-dev-app.mjs \
--remote-debugging-port="$CDP_PORT" \
--no-quit-confirmation
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.
- 10d ago First seen · 109 lines · 54 tokens per session scan A 3ae60e0064f4
neon-pilot-parallel-qa is a skill published in the GitHub repository patleeman/neon-pilot (23 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,146 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
pyats-dynamic-test
Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.
test-loop
Plan, generate, and heal an executable E2E test suite from approved acceptance criteria (web and mobile).
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…