agentmods.dev

ingest-01-happy

ingest-01-happy is a command for Claude Code from evb87-tech/corpus. It costs 0 tokens per session (575 once invoked), scanned A, original, MIT.

A test scenario for importing a French source into a research wiki. It checks that one source becomes several linked, source-cited pages about product-management topics.

In plain words
What is it for?
Testing ingestion of topics such as OKRs, product requirements documents, sprint reviews, product debt, and roadmaps.
Why use it?
It ensures imported knowledge is organized, traceable to its source, written in French, and added to the wiki index and log.

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

not rated 1 4mo ago A scan 0 tokens original MIT
View the source file evb87-tech/corpus
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/ingest-01-happy
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 ingest-01-happy

README.md
[![agentmods](https://agentmods.dev/badge/commands/evb87-tech/corpus/ingest-01-happy.svg)](https://agentmods.dev/commands/evb87-tech/corpus/ingest-01-happy)
Your own site
<a href="https://agentmods.dev/commands/evb87-tech/corpus/ingest-01-happy"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/ingest-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 575 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00575
Opus 5 $0.00000 $0.00287
Sonnet 5 $0.00000 $0.00115
Haiku 4.5 $0.00000 $0.00057

Measured 5d ago against content hash 6e1bca6b991c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ingest-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 5d 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/ingest-01-happy.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scénario

Une source francophone sur la gestion de produit est déposée dans raw/. On lance /ingest sur ce fichier. Le comportement attendu est la création de 10 à 15 pages wiki en français, avec frontmatter valide, citations sources: renseignées, et mise à jour de wiki/index.md et wiki/log.md.

Setup

Créer le fichier suivant dans $CORPUS_VAULT/raw/ :

raw/cmd-ingest-fr-source.md (voir evals/fixtures-commands/cmd-ingest-fr-source.md)

La source couvre plusieurs entités distinctes : méthodologie OKR, définition d'un PRD, rituel de sprint review, notion de dette produit, et concept de roadmap. Elle est rédigée entièrement en français et ne comporte pas de contradictions internes.

Prompt

/ingest raw/cmd-ingest-fr-source.md

Pass criteria (rubric)

  • Entre 10 et 15 pages sont créées dans wiki/ (noms kebab-case ASCII, sans accents).
  • Chaque page wiki créée contient un frontmatter avec sources: [raw/cmd-ingest-fr-source.md].
  • Le corps de chaque page est rédigé en français. Les mots-clés structurels (noms H2 canoniques, clefs frontmatter) restent en anglais.
  • wiki/index.md est mis à jour avec les nouvelles entrées.
  • Une entrée est ajoutée dans wiki/log.md avec la date du jour.
  • Le récapitulatif final mentionne le nombre de pages créées, le nombre de pages modifiées, les contradictions détectées (aucune ici), et les liens brisés.
  • Aucune écriture n'a lieu dans raw/ ni dans output/.

Fail signals

  • Moins de 5 pages créées (ingestion trop sélective) ou plus de 20 (ingestion trop granulaire ou redondante).
  • Une ou plusieurs pages wiki ne contiennent pas le champ sources: en frontmatter.
  • Le corps d'une page est rédigé en anglais (la source est en FR — aucune traduction n'est nécessaire, mais le corps doit rester FR).
  • Un mot-clé structurel (ex. ## Ce que disent les sources) est traduit en français dans le frontmatter YAML.
  • wiki/index.md n'est pas mis à jour.
  • Un fichier est écrit dans raw/ ou output/.

Read the full file on GitHub · 55 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. 5d ago First seen · 55 lines · 0 tokens per session scan A 6e1bca6b991c

Subscribe to this mod's changes

ingest-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 575 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.

LLMResearchclaude-codeclaude-code-marketplaceclaude-code-pluginknowledge-managementobsidian
Related

Other commands, from other repositories

save

Manually save current context as a memo to the memex vault.

linxule/memex-plugin · 13 tokens

open

Open the memex vault in Finder or Obsidian.

linxule/memex-plugin · 11 tokens

sol

Run a one-shot task on the routed Codex model (gpt-5.6-sol by default) and relay its answer.

AiAi-Mastermind/aiai-mastermind-tools-and-skills · 26 tokens

codex-usage

Show your ChatGPT/Codex weekly usage limits (via the local model-router proxy).

AiAi-Mastermind/aiai-mastermind-tools-and-skills · 18 tokens

fabsol

Run the FabSol flow - your main model orchestrates, the routed worker model builds.

AiAi-Mastermind/aiai-mastermind-tools-and-skills · 17 tokens

release

Generate changelog, bump version, and create git tag.

Joncik91/ucai · 11 tokens