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 instructions/endle/fireseqsearch/claude-mdgit clone --depth 1 https://github.com/Endle/fireSeqSearchWhat 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 | $0.02621 | $0.02621 |
| Opus 5 | $0.01311 | $0.01311 |
| Sonnet 5 | $0.00524 | $0.00524 |
| Haiku 4.5 | $0.00262 | $0.00262 |
Grade A, and why
fireSeqSearch CLAUDE.md 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 2d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fireSeqSearch
Local search server + browser extension that appends hits from your Logseq/Obsidian notebook to Google search results. Architecture is LLM-first: dense semantic retrieval over the user's notes plus per-page LLM-generated summaries, with the goal of making search results explain themselves at a glance.
Surface area
/query/:term— semantic search, sub-second. Returns rankedPageHits (title,logseq_uri,score,chunk_id,top_snippet,summary,summary_status).POST /ask— deliberate Q&A. Body{question, k?}; SSEmeta(sources +confidence) →delta*→done({cited, invalid, chars, answered, confidence}) orerror. Cited[N]markers validated against the retrieved set; anything invented lands indone.invalid.POST /reindex— manual rescan trigger./server_info— config + indexer/summarizer counts + crate version + capabilities. Addon hard-floors onMIN_BACKEND_VERSIONand soft-gates UI oncapabilities.POST /highlight— dormant; kept as scaffolding for a future "explain this card" action.
Locked decisions — don't relitigate without strong evidence
Retrieval
- Embedding:
bge-m3(1024-dim, multilingual, 8K context), Q4_K_M GGUF. Chosen to take retrieval quality off the debug list. - Index: flat in-memory
Vec<(ChunkId, [f32; 1024])>, brute-force cosine. No ANN, no vector DB. ~10K chunks fits under 50ms. - Storage: SQLite (
notes+chunks, raw f32 LE BLOBs). Storage, not a search index — all rows hydrate into the in-memory vec on startup. - Change detection: mtime as fast filter, Blake3
content_hashas truth. - Dual signal:
note_score = max(best_chunk · query, summary · query). Pages whose gist matches rise even when no individual chunk does. CHUNKER_VERSIONinstore.rs— bump it when chunker logic changes. Stale chunks otherwise hash-match and skip re-embedding forever.
Chunking (flavour-aware via --notebook obsidian)
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.
- 2d ago First seen · 181 lines · 2,621 tokens per session scan A 614302737743
fireSeqSearch CLAUDE.md is an instructions file published in the GitHub repository Endle/fireSeqSearch (108 stars, last pushed 10d ago), licensed MIT. It adds 2,621 tokens to every session, about $0.0131 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 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.