What is live-corpus-search?

Live Corpus Search is a procedure for testing search and indexing changes against the real Ragdocs documentation collection.

Use it after changing search, indexing, or search-kernel behavior in the Ragdocs repository.

It checks that the installed background service is running the current code and that search results work with the actual multi-project data.

How andnp/ragdocs-mcp configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to andnp/ragdocs-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/andnp/ragdocs-mcp/main/.github/skills/live-corpus-search/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/andnp/ragdocs-mcp

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andnp/ragdocs-mcp/live-corpus-search/github.svg)](https://agentmods.dev/skills/andnp/ragdocs-mcp/live-corpus-search)

Your own site

<a href="https://agentmods.dev/skills/andnp/ragdocs-mcp/live-corpus-search"><img src="https://agentmods.dev/badge/skills/andnp/ragdocs-mcp/live-corpus-search/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andnp/ragdocs-mcp/live-corpus-search"><img src="https://agentmods.dev/badge/skills/andnp/ragdocs-mcp/live-corpus-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 656 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00032	$0.00656
Opus 5	$0.00016	$0.00328
Sonnet 5	$0.00006	$0.00131
Haiku 4.5	$0.00003	$0.00066

Measured 10d ago against content hash e8540569d88f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

live-corpus-search 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 10d 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.

.github/skills/live-corpus-search/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Live Corpus Search

When to Use

Verify a local search or indexing change against the real multi-project corpus.
Confirm that the globally installed Ragdocs daemon is running the current checkout.
Compare JSON query results before and after a search change.

Procedure

From the Ragdocs repository, refresh the global editable tool:
```
uv tool install --editable --force /home/andy/Projects/personal/mcp-markdown-ragdocs
```
Confirm that the install resolves the expected andnp-searchkernel version.
Restart the global daemon with enough time for the corpus to initialize:
```
mcp-markdown-ragdocs daemon restart --timeout 120
```
The default 10-second timeout is often too short for the live corpus.
Wait for readiness before querying:
```
mcp-markdown-ragdocs daemon status
mcp-markdown-ragdocs index stats
```
Continue only when daemon status is running and index stats report Index state: ready with Remaining estimate: 0. If restart times out, inspect status again; the daemon may still be initializing. Use the daemon log at: /home/andy/.local/state/mcp-markdown-ragdocs/daemon/daemon.log.
Run queries one at a time. Do not launch concurrent CLI queries while the daemon is starting or rebuilding:
```
mcp-markdown-ragdocs query "your query" --top-n 5 --json
```
Use --project-filter mcp-markdown-ragdocs when evaluating the current repository's documents instead of the whole global corpus:
```
mcp-markdown-ragdocs query "your query" \
  --project-filter mcp-markdown-ragdocs --top-n 5 --json
```
Summarize results using file_path, header_path, score, and provenance.strategies. Include both positive queries and an unrelated query when checking relevance and abstention behavior:
```
... --json | jq -r \
  '.results[] | [.file_path, .header_path, .score,
    (.provenance.strategies | join(","))] | @tsv'
```

Operational Notes

The daemon is global; daemon restart operates on ~/.local/state/mcp-markdown-ragdocs/daemon.
Querying without --project-filter searches all configured document roots and indexed Git history, which can outrank a relevant document from the current repository.
A relevant result appearing in the corpus does not prove it is ranked first. Record the query, scope, top results, scores, and retrieval strategies.
The CLI does not expose every search policy parameter. Use the MCP/API surface when testing thresholds or other request-level filters.

Read the full file on GitHub · 64 lines

Changes

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.

10d ago First seen · 64 lines · 32 tokens per session scan A e8540569d88f

Subscribe to this mod's changes

live-corpus-search is a skill published in the GitHub repository andnp/ragdocs-mcp (2 stars, last pushed 13d ago), licensed MIT. It adds 32 tokens to every session and 656 once invoked, about $0.0002 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

ragdocs-mcp: Skill for Claude Code