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 skills/gethouston/houston/verifynpx skills add gethouston/houston --skill verifygit clone --depth 1 https://github.com/gethouston/houstonWrote 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/gethouston/houston/verify)<a href="https://agentmods.dev/skills/gethouston/houston/verify"><img src="https://agentmods.dev/badge/skills/gethouston/houston/verify.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 | $0.00033 | $0.00488 |
| Opus 5 | $0.00016 | $0.00244 |
| Sonnet 5 | $0.00007 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
verify scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:48123/health What it actually says
Verifying Houston changes at runtime
TS host (the real desktop sidecar), hermetically
mkdir -p /tmp/hh/workspaces/Personal/"Agent 1"
HOUSTON_HOME=/tmp/hh HOUSTON_HOST_PORT=48123 HOUSTON_HOST_TOKEN=t \
node --import tsx packages/host/src/local/main.ts
# wait for {"status":"ok"}:
curl -s http://127.0.0.1:48123/health
- Auth:
Authorization: Bearer t. Agent ids are<Workspace>/<Agent>— URL-encode the slash (/agents/Personal%2FAgent%201/files). - SSE reactivity feed:
curl -N 'http://127.0.0.1:48123/v1/events?token=t'. - The runtime is only spawned for chat turns; files/agents routes need no provider credentials.
Web UI (the same React tree the desktop ships)
Playwright + the fake host (@houston/fake-host), all boot handled by the
harness:
pnpm --filter houston-web test:e2e # whole suite
cd packages/web && npx playwright test e2e/files.spec.ts --reporter=line
- Specs live in
packages/web/e2e/; fixtures reset the fake host per test. - One-off screenshots: drop a temp spec in
e2e/,page.screenshot(...), delete it after (testDir is pinned toe2e/). - Gotchas: controlled inputs never match
input[value=…](usegetByRole("textbox")); headless Chromium names blob downloads with a GUID — assert downloaded bytes, notsuggestedFilename().
Gates (CI-equivalent, not a substitute for the above)
pnpm check · pnpm typecheck (ui+app+web) · pnpm --filter @houston/host test
· cd app && pnpm check-locales · pnpm check:boundaries
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.
- 5d ago First seen · 45 lines · 33 tokens per session scan A c36e9add6fc5
verify is a skill published in the GitHub repository gethouston/houston (112 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 488 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
run-integration-tests
Build, pack, and run .NET MAUI integration tests locally. Validates templates, samples, and end-to-end scenarios using the local workload.
cli-e2e-testcase-writer
Use when adding or updating Go CLI E2E coverage for one tests/clie2e/{domain} domain of the compiled lark-cli, especially when the work requires live --help or schema exploration, scenario-based clie2e.RunCmd workflows, and per-domain coverage.md maintenance.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
__SKILL_ID__
This fixture verifies that skill content can be written into the target sandbox and queried back immediately.
harness-test-writer
Add regression test cases to the Bifrost provider harness (the Postman collection run via make run-provider-harness-test) based on a merged PR or a GitHub issue. Fetches the PR/issue, traces the affected wire path in the codebase, checks existing harness coverage, designs cases following harness conventions, inserts…