What is dogfood-live-corpus?

A testing skill that uses a separate agent to query a live Ragdocs document-search collection and report evidence-based search-quality problems. Ragdocs is a system that indexes documents so they can be searched and ranked.

Use it before or during search-system improvements to run controlled queries, inspect the service and index state, find quality gaps, and produce an improvement report.

It provides feedback from real indexed data instead of relying only on assumptions or small test examples. This helps evaluate changes to searching, indexing, ranking, or the search engine itself.

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/dogfood-live-corpus/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/dogfood-live-corpus/github.svg)](https://agentmods.dev/skills/andnp/ragdocs-mcp/dogfood-live-corpus)

Your own site

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

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,370 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	$0.00031	$0.01370
Opus 5	$0.00015	$0.00685
Sonnet 5	$0.00006	$0.00274
Haiku 4.5	$0.00003	$0.00137

Measured 11d ago against content hash 598389521038, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dogfood-live-corpus 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 11d 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/dogfood-live-corpus/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dogfood the Live Corpus

When to Use

Evaluate search, indexing, ranking, graph, or searchkernel changes against real data.
Run a recurring search-quality feedback loop without consuming the parent agent's context.
Generate improvement hypotheses before implementation.

Parent Agent Setup

Refresh the global editable install:

uv tool install --editable --force /home/andy/Projects/personal/mcp-markdown-ragdocs

Restart the global daemon with a corpus-sized timeout:
```
mcp-markdown-ragdocs daemon restart --timeout 120
```
Wait for readiness:
```
mcp-markdown-ragdocs daemon status
mcp-markdown-ragdocs index stats
```
Continue only when the daemon is running and the index reports Index state: ready with Remaining estimate: 0.
Delegate the audit to one general-purpose subagent using the gpt-5.6-luna model. The subagent must work read-only and run queries sequentially, never concurrently while the daemon is starting or rebuilding.

Lifecycle Validity Gates

Before the first query, capture JSON snapshots from daemon status --json, queue status --json, and index stats --json. Record the daemon pid, status, and lifecycle, plus index index_state.status, remaining_estimate, pending_count, running_count, and failed_count.

Require the pre-query snapshot to show one ready daemon PID, a ready index, remaining_estimate: 0, and no pending or running tasks. After the query portfolio, capture the same three snapshots again. The run is invalid if the PID changes, readiness regresses, or any new pending/running/failed work appears without an explicitly documented corpus change. A transient query failure does not waive this gate: capture the post-query state and report any replacement, rebuild, or queue churn before interpreting search results.

Use --json for all six snapshots so PID, readiness, and queue/task values can be compared mechanically. Preserve the snapshots with the audit report.

Read the full file on GitHub · 132 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.

11d ago First seen · 132 lines · 31 tokens per session scan A 598389521038

Subscribe to this mod's changes

dogfood-live-corpus is a skill published in the GitHub repository andnp/ragdocs-mcp (2 stars, last pushed 14d ago), licensed MIT. It adds 31 tokens to every session and 1,370 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.

Research 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