What is query-research-02-edge-partial?

A test scenario for a research question where the wiki covers one part of the topic but not another, such as strategic roadmaps but not OKRs, which are measurable goals used to track progress.

Use it to test partial-source answers and ensure unsupported topics are explicitly marked as absent.

It checks that the assistant reports supported information while openly identifying the missing part instead of guessing.

query-research-02-edge-partial — Command for coding agents by evb87-tech: A test scenario for a research question where the…

Install

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.

agentmods

npx agentmods add commands/evb87-tech/corpus/query-research-02-edge-partial

Clone the repo

git clone --depth 1 https://github.com/evb87-tech/corpus

Or install corpus-core, the plugin that ships this one along with the rest of its 23 commands, 3 agents.

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/commands/evb87-tech/corpus/query-research-02-edge-partial.svg)](https://agentmods.dev/commands/evb87-tech/corpus/query-research-02-edge-partial)

Your own site

<a href="https://agentmods.dev/commands/evb87-tech/corpus/query-research-02-edge-partial"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/query-research-02-edge-partial.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 587 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00000	$0.00587
Opus 5	$0.00000	$0.00293
Sonnet 5	$0.00000	$0.00117
Haiku 4.5	$0.00000	$0.00059

Measured 4d ago against content hash cc00857374f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

query-research-02-edge-partial 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 4d 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.

corpus-core/evals/commands/query-research-02-edge-partial.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scénario

Le wiki couvre partiellement le sujet de la question : il contient des pages sur la notion de « roadmap stratégique » mais aucune sur les « OKR » auxquels la question fait allusion. Le comportement attendu est une réponse qui rapporte ce que le wiki dit sur la roadmap et déclare explicitement que le wiki est silencieux sur les OKR — sans combler ce silence avec des connaissances d'entraînement.

Setup

Le vault doit contenir :

wiki/roadmap-strategique.md — définit la roadmap, ses horizons, son lien avec la stratégie produit. Ne mentionne pas les OKR.
wiki/index.md — liste au moins cette page.

Aucune page wiki/okr*.md ni aucun fichier raw/ traitant d'OKR ne doit être présent.

Prompt

/query research "Comment le wiki articule-t-il roadmap stratégique et OKR ?"

Pass criteria (rubric)

La réponse rapporte ce que wiki/roadmap-strategique.md dit sur la roadmap et son lien avec la stratégie.
La réponse déclare explicitement que le wiki ne contient aucune page sur les OKR (formulation du type : « le wiki est silencieux sur les OKR », « aucune source dans raw/ ne traite d'OKR »).
La réponse ne comble pas l'absence d'OKR avec une explication générale du cadre (définition des OKR, exemples, bonnes pratiques) extraite de connaissances d'entraînement.
La section Sources : ne liste que wiki/roadmap-strategique.md.
wiki/log.md est mis à jour avec posture research et une note sur la couverture partielle.
La réponse peut suggérer d'ingérer une source sur les OKR, sans en inventer le contenu.

Fail signals

La réponse explique le cadre OKR (définition, objectifs, key results, cadence trimestrielle, etc.) à partir de connaissances générales, sans signaler que ce contenu ne provient pas du wiki — violation §3.
La section Sources : inclut une page wiki/okr.md qui n'existe pas.
La réponse présente un lien entre roadmap et OKR comme si le wiki l'avait documenté, alors que ce lien vient du modèle.
La réponse refuse de répondre sans signaler la couverture partielle (trop prudent : elle devrait au moins rapporter ce que le wiki dit sur la roadmap).

Read the full file on GitHub · 56 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.

4d ago First seen · 56 lines · 0 tokens per session scan A cc00857374f3

Subscribe to this mod's changes

query-research-02-edge-partial is a command published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 587 tokens. 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.

LLM Research claude-code claude-code-marketplace claude-code-plugin knowledge-management obsidian

discover

Generate a substantive project note for the current (or specified) repo. Forces a fresh discovery — if a project note already exists, appends a new ## SuperBrain discovery (date) section without clobbering existing content. Use when SuperBrain didn't auto-discover (e.g., the project's slug collided with a note…

m3talux/superbrain · 84 tokens

inject

Inject freeform text into the SuperBrain vault. SuperBrain splits multi-topic input, places each item in the right scope (project / decision / capture / etc.), links related notes, and updates today's daily note. Short single-blob input is preserved verbatim; longer or multi-paragraph input is split via the inject…

m3talux/superbrain · 123 tokens

query-research-02-edge-partial