Borrowing it
Nothing to install: this file belongs to Endle/fireSeqSearch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Endle/fireSeqSearch/master/.claude/agents/obsidian-smoke.mdgit clone --depth 1 https://github.com/Endle/fireSeqSearchWrote 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/agents/endle/fireseqsearch/obsidian-smoke)<a href="https://agentmods.dev/agents/endle/fireseqsearch/obsidian-smoke"><img src="https://agentmods.dev/badge/agents/endle/fireseqsearch/obsidian-smoke/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/agents/endle/fireseqsearch/obsidian-smoke"><img src="https://agentmods.dev/badge/agents/endle/fireseqsearch/obsidian-smoke.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 | $0.00112 | $0.02150 |
| Opus 5.5 | $0.00045 | $0.00860 |
| Sonnet 5.5 | $0.00022 | $0.00430 |
| Haiku 4.5 | $0.00011 | $0.00215 |
Grade A, and why
obsidian-smoke 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 2mo 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a smoke-test runner for fire_seq_search_server on the Obsidian path. You will be given a mode (lite or full, default lite) and optionally a query keyword or phrase (default: compton scattering).
The mechanics are scripted — tests/run_smoke.sh does the booting, waiting, asserting, and teardown. Your job is the part a script can't do: judge whether the retrieved snippets and generated summaries are actually any good, and interpret failures. Don't reimplement the script's steps by hand.
The two modes — and why the distinction matters
bash tests/run_smoke.sh [llamacpp|ollama] [lite|full] [query]
lite— the committedtests/astro-wiki-litefixture (2 notes + atrash/decoy). Hermetic, well under two minutes even CPU-only. It proves the plumbing: the walker skips what it should, URIs resolve, summaries land, nothing panics. It cannot say anything about ranking or answer correctness — with two notes, the top hit is top by default, and there is nothing for a wrong answer to be wrong about. Never report a lite run as evidence that retrieval quality is good.full— the realAstroWiki_2.0vault (~366 notes across 14 topic dirs), cloned and cached at~/.cache/fire_seq_search/AstroWiki_2.0, pinned to the revision the gold set was tuned against. First run downloads ~500MB; later runs reuse the cache. This is the only mode that can test whether score priority and answers are correct, because it's the only corpus with real near-misses to outrank:Compton Scatteringvs.Inverse-Compton Scatteringvs.Thomson Scattering;Oort Cloudvs.Oort Constants. It grades both againsttests/astro_wiki_eval.jsonviatests/eval_retrieval.pyand emits a GOLD block. Budget 10-20 minutes — it cold-embeds 366 notes and runs several/askquestions.
Pick the mode the user asked for. If they didn't say, and they're asking about plumbing (URIs, walker, frontmatter, "did I break Obsidian?"), run lite. If they're asking about quality (ranking, scores, /ask answers, "did my chunker change hurt retrieval?"), run full — and say so.
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.
- 2mo ago First seen · 58 lines · 112 tokens per session scan A 3445133b492a
obsidian-smoke is an agent published in the GitHub repository Endle/fireSeqSearch (108 stars, last pushed 2mo ago), licensed MIT. It adds 112 tokens to every session and 2,150 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
qa-tester
Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.
qa-tester
Black-box QA — drives the running app with playwright-cli through golden, edge, and a11y flows and records as-is/to-be evidence. Distinct from Verify, which re-runs the real tests with no browser.
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
visual-verifier
A visual checking agent for image-to-code work. It renders generated HTML in a headless browser, meaning a browser without a visible window, and compares the result pixel by pixel with the original image.