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 skills add timurgaleev/memex --skill smoke-testgit clone --depth 1 https://github.com/timurgaleev/memexWrote 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/timurgaleev/memex/smoke-test)<a href="https://agentmods.dev/skills/timurgaleev/memex/smoke-test"><img src="https://agentmods.dev/badge/skills/timurgaleev/memex/smoke-test/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/timurgaleev/memex/smoke-test"><img src="https://agentmods.dev/badge/skills/timurgaleev/memex/smoke-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.01635 |
| Opus 5.5 | $0.00022 | $0.00654 |
| Sonnet 5.5 | $0.00011 | $0.00327 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade A, and why
smoke-test 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.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smoke Test Skillpack
Walk the check list below after any container restart. There is no smoke-test binary — every check is a real
memexcommand you run and read.
Contract
This skill guarantees:
- 6 core checks verify memex server health after restart
- Each check is a real command, not a wrapper script
- Known failures are auto-fixed before reporting
- Results are reported as a single summary line plus per-check status
- The reported failure count = checks still broken after auto-fix (0 = all pass)
The Check List
| # | Check | Command | Auto-Fix |
|---|---|---|---|
| 1 | Server answers + config sane | memex status |
Restart the service |
| 2 | Database, sources, brain health | memex doctor |
Per-finding (doctor names the cause) |
| 3 | Background cycle ran recently | memex status (cycle timestamp) |
Kick a manual memex cycle |
| 4 | Secrets + Bedrock reachable | memex doctor (auth findings) |
Re-run the fetch-secrets step, restart |
| 5 | Read path returns hits | memex call search '{"q":"<known topic>"}' |
Re-index, then memex embed |
| 6 | Write path round-trips | page_put → page_get (see below) |
— (escalate; a broken write path is not self-healing) |
Checks 1-4 are read-only. Check 5 reads. Check 6 writes one throwaway page and reads it back.
Usage
From a shell on the host
memex status
memex doctor
memex call search '{"q":"<a topic you know is indexed>"}'
Write-path round-trip (check 6)
memex call page_put '{"slug":"reports/smoke/_probe","markdown_body":"# probe\nsmoke check"}'
memex call page_get '{"slug":"reports/smoke/_probe"}'
The page_get must return the content the page_put just wrote. Reuse the
same slug every run — the probe page is overwritten, not accumulated.
From an agent without shell access
The same checks run over MCP: get_status_snapshot (1, 3), run_doctor (2, 4),
search (5), page_put + page_get (6). Read-only checks are identical; the
auto-fixes that need a service restart aren't available over MCP — report them
instead.
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 Changed 5018a72f2242
- 1mo ago First seen · 164 lines · 55 tokens per session scan A 1f775104ce0b
smoke-test is a skill published in the GitHub repository timurgaleev/memex (11 stars, last pushed 26d ago), licensed MIT. It adds 55 tokens to every session and 1,635 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 2026-08-31.
Other skills, from other repositories
field-test
Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, measures every call (bytes, token estimate, wall-clock) and weighs the catalog, renders app tools' views in a headless MCP Apps host, and produces a…
field-test
Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, measures every call (bytes, token estimate, wall-clock) and weighs the catalog, renders app tools' views in a headless MCP Apps host, and produces a…
playwright-qa
Automated visual QA testing using Playwright — navigate web apps like a real user, capture screenshots, find bugs, and fix them.
release-parity-test
Use before cutting a release, after a change to live reads, write tools or skills, or when the user asks to test the MCP against the web app. Runs the three-way parity test in test-matrix.md (cache mode vs live MCP vs app.copilot.money), including round-trip writes with throwaway test data in the user's Manual…
atf-testing
Build ServiceNow Automated Test Framework tests and suites — impersonation, form steps, assertions, server-side script steps, test parameters, and execution via snowcreateatftest / snowexecuteatftest.
gstack-qa
QA lead with real browser testing. Tests your app, finds bugs, fixes them with atomic commits, generates regression tests. Use when the user says "QA", "test this", "find bugs", "exploratory test", "QA this", or "test the app".