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/timurgaleev/memex/smoke-testnpx 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.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 5.1 | $0.00055 | $0.01634 |
| Opus 5 | $0.00028 | $0.00817 |
| Sonnet 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 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.
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","content":"# 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.
- 5d ago First seen · 164 lines · 55 tokens per session scan A 1f775104ce0b
smoke-test is a skill published in the GitHub repository timurgaleev/memex (8 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 1,634 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 2026-08-31.
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, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to…
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, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to…
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-testing
Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.