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.
npx agentmods add commands/dork-labs/dorkos/maintaingit clone --depth 1 https://github.com/dork-labs/dorkosWrote 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/commands/dork-labs/dorkos/maintain)<a href="https://agentmods.dev/commands/dork-labs/dorkos/maintain"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/maintain.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.00900 |
| Opus 5 | $0.00005 | $0.00450 |
| Sonnet 5 | $0.00002 | $0.00180 |
| Haiku 4.5 | $0.00001 | $0.00090 |
Grade A, and why
maintain 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 3d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Test Maintenance
Audit the browser test suite health, detect stale and orphaned tests, and auto-update broken tests.
Maintenance Flow
Step 1: Read Manifest
Read apps/e2e/manifest.json to get the list of all tracked tests. If the manifest is empty or has no tests, report that and stop.
Step 2: Audit Each Test
For each test entry in the manifest:
- Check existence: Glob for
apps/e2e/<specFile>to verify the spec file still exists on disk - Check staleness: If the test has
relatedCodeentries, check if any were modified sincelastRun:
If any output, the test is potentially stale.git log --since="<lastRun>" --oneline -- <relatedCode paths> - Run the test: Execute the individual test to check if it passes:
cd apps/e2e && npx playwright test <specFile> --reporter=json 2>&1
Step 3: Categorize Results
Classify each test into one of four categories:
- Healthy — Test passes AND related code unchanged since last run
- Stale — Test passes BUT related code was modified since last run (may need updating)
- Broken — Test fails (selector changed, timing issue, or code regression)
- Orphaned — Spec file still exists but related source code files have been deleted
Step 4: Auto-Fix Stale Tests
For stale tests:
- Use Playwright MCP
mcp__plugin_playwright_playwright__browser_navigateto visit the feature athttp://localhost:6241 - Use
mcp__plugin_playwright_playwright__browser_snapshotto capture the current accessibility tree - Compare current selectors/structure with what the test expects
- Update POM locators or test assertions if they've drifted
- Re-run the test to verify the update works
Step 5: Handle Orphaned Tests
For orphaned tests:
- Display the list of orphaned tests to the user
- Ask for confirmation using AskUserQuestion before removing anything
- If confirmed: delete the spec file and remove the entry from manifest.json
- If declined: keep the test but flag it in the report
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.
- 3d ago First seen · 100 lines · 9 tokens per session scan A 4fa5f57d2a83
maintain is a command published in the GitHub repository dork-labs/dorkos (9 stars, last pushed 3d ago), licensed MIT. It adds 9 tokens to every session and 900 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
test-run
Run all tests and report coverage to @chief.
e2e
Generate and execute end-to-end tests for user workflows using Playwright.
dark-factory-behavioral-e2e
Holdout-pattern E2E validator. Drives agent-browser against the running DynaChat app to verify that the PR's user-facing behavior actually matches what the linked issue asked for.
dark-factory-test-rag-response
Comprehensive test scenario 3 - verify RAG pipeline grounds answers in ingested video and surfaces citations.
dark-factory-test-video-ingestion
Comprehensive test scenario 2 - verify adding a YouTube video to the library works end-to-end.
dark-factory-test-chat-ui
Comprehensive test scenario 1 - verify chat UI loads, accepts input, and renders a response.