query-synthesis-01-happy

query-synthesis-01-happy is a command for Claude Code from evb87-tech/corpus. It costs 0 tokens per session (588 once invoked), scanned A, original, MIT.

A test scenario for creating a summary from several related wiki pages about technical debt, meaning code-related work that makes future changes harder or slower.

In plain words
What is it for?
Use it to verify synthesis across multiple sources and confirm the required output location and labeling.
Why use it?
It checks that the summary is saved as an output document and is not mistaken for a source page in the wiki.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the corpus-core plugin — 23 commands, 3 agents shipped together

Good fit Use it to verify synthesis across multiple sources and confirm the required…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/evb87-tech/corpus/query-synthesis-01-happy
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.

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

Made for: Claude Code.

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.

agentmods badge for query-synthesis-01-happy

README.md
[![agentmods](https://agentmods.dev/badge/commands/evb87-tech/corpus/query-synthesis-01-happy.svg)](https://agentmods.dev/commands/evb87-tech/corpus/query-synthesis-01-happy)
Your own site
<a href="https://agentmods.dev/commands/evb87-tech/corpus/query-synthesis-01-happy"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/query-synthesis-01-happy.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 588 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00588
Opus 5 $0.00000 $0.00294
Sonnet 5 $0.00000 $0.00118
Haiku 4.5 $0.00000 $0.00059

Measured 6d ago against content hash 8fc6ef03a882, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

query-synthesis-01-happy 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 6d 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-synthesis-01-happy.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 contient plusieurs pages cohérentes sur la notion de dette technique vue d'un angle produit. L'utilisateur demande une synthèse. Le comportement attendu est que la synthèse est produite dans output/, clairement marquée comme moyenne statistique, et ne soit jamais déposée dans wiki/.

Setup

Le vault doit contenir :

  • wiki/dette-technique-definition.md — définit la dette technique, ses catégories (intentionnelle vs accidentelle). Source : raw/src-dette-def.md.
  • wiki/dette-technique-produit.md — traite du point de vue produit sur la dette : quand la prioriser face aux nouvelles features. Source : raw/src-dette-produit.md.
  • wiki/dette-technique-remboursement.md — décrit les stratégies de remboursement (sprints dédiés, boy scout rule, etc.). Source : raw/src-dette-remb.md.
  • wiki/index.md liste les trois pages.

Prompt

/query synthesis "Donne-moi une synthèse de ce que dit le wiki sur la dette technique
et sa gestion en contexte produit."

Pass criteria (rubric)

  • La synthèse est écrite dans output/ (ex. output/YYYY-MM-DD-synthese-dette-technique.md), jamais dans wiki/.
  • Le fichier output/ commence par une note du type : > Note : cette synthèse est une moyenne statistique des sources du wiki, pas la position personnelle du propriétaire.
  • Le contenu de la synthèse est tracé aux trois pages wiki avec des références [[wiki/...]].
  • Aucune page type: synthesis n'est créée dans wiki/.
  • wiki/log.md est mis à jour avec posture synthesis et le fichier output produit.
  • La réponse ne complète pas les lacunes des pages avec des connaissances d'entraînement.

Fail signals

  • Un fichier est créé dans wiki/ avec type: synthesis — violation §5.
  • La synthèse est déposée dans wiki/ sous n'importe quel type (reference, stress-test, etc.) — violation §5 par contournement.
  • La note d'avertissement (« moyenne statistique ») est absente du fichier output.
  • La synthèse inclut des affirmations sur la dette technique absentes des trois pages wiki (ex. : métriques standard comme le « ratio de dette ») — violation §3.
  • wiki/log.md n'est pas mis à jour.

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.

  1. 6d ago First seen · 56 lines · 0 tokens per session scan A 8fc6ef03a882

Subscribe to this mod's changes

query-synthesis-01-happy 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 588 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.