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.
npx skills add Ludovic33Fr/product-ai-toolbox --skill committee-prepgit clone --depth 1 https://github.com/Ludovic33Fr/product-ai-toolboxWrote 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.
[](https://agentmods.dev/skills/ludovic33fr/product-ai-toolbox/committee-prep)<a href="https://agentmods.dev/skills/ludovic33fr/product-ai-toolbox/committee-prep"><img src="https://agentmods.dev/badge/skills/ludovic33fr/product-ai-toolbox/committee-prep/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.
<a href="https://agentmods.dev/skills/ludovic33fr/product-ai-toolbox/committee-prep"><img src="https://agentmods.dev/badge/skills/ludovic33fr/product-ai-toolbox/committee-prep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00054 | $0.01436 |
| Opus 5 | $0.00027 | $0.00718 |
| Sonnet 5 | $0.00011 | $0.00287 |
| Haiku 4.5 | $0.00005 | $0.00144 |
Grade A, and why
committee-prep 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
committee-prep
Fiche éditoriale
Objectif. Préparer un comité d'arbitrage avec dossier de fond et anticipation des objections.
Entrées. Sujet, recommandation provisoire, données disponibles, liste des participants.
Sorties. Synthèse des données, contre-arguments classés, objections anticipées par participant, formulation médiane, critères de décision.
Cadence d'usage. Avant chaque comité d'arbitrage majeur.
Mode opératoire
Quand m'invoquer
L'utilisateur prépare un comité d'arbitrage (steerco, comité produit, instance de décision) et me fournit le sujet, sa recommandation provisoire, les données qu'il a en main, et la liste des participants attendus. Il veut un dossier qui anticipe la dynamique de la réunion.
Procédure
- Synthèse des données : reformuler ce qui est documenté en 5 à 8 puces factuelles. Distinguer faits observés et hypothèses.
- Contre-arguments : générer les trois meilleurs contre-arguments à la recommandation, classés par force décroissante. Pour chacun, donner ce qui le réfute si possible.
- Cartographie des participants : pour chaque participant, identifier sa position probable (favorable / neutre / opposé) et son angle de préoccupation principal (technique, commercial, financier, RH, juridique, etc.). Si les positions ne sont pas connues, le dire.
- Objections anticipées : pour chaque participant identifié comme neutre ou opposé, formuler 1 à 2 objections probables et la réponse préparée.
- Formulation médiane : proposer une version intermédiaire de la recommandation, qui pourrait émerger comme compromis si la position initiale n'est pas validée. Préciser ce qu'on perd et ce qu'on gagne.
- Critères de décision : expliciter les critères sur lesquels la décision devrait se prendre, et signaler s'ils sont implicites ou divergents entre participants.
- Produire la sortie au format ci-dessous.
Format de sortie
# Dossier comité — {sujet}
*{date du comité} — préparé le {date du jour}*
## Recommandation soumise
> {1-3 phrases — recommandation à arbitrer}
## Synthèse des données (5-8 puces)
- {fait factuel} *(source : {référence})*
- ...
## Contre-arguments (par force décroissante)
### 1. {contre-argument principal}
{explication courte}
**Réfutation possible** : {élément qui désamorce}
### 2. ...
### 3. ...
## Cartographie des participants
| Participant | Position probable | Angle de préoccupation |
|-------------|-------------------|------------------------|
| {nom} | favorable / neutre / opposé / inconnu | technique / commercial / financier / juridique / RH / autre |
## Objections anticipées et réponses
### {participant 1}
- **Objection** : {formulation probable}
- **Réponse préparée** : {1-2 phrases}
### {participant 2}
...
## Formulation médiane
> {version compromis de la recommandation}
**Ce qu'on gagne** : {bénéfice de la médiane}
**Ce qu'on perd** : {compromis assumé}
## Critères de décision
- {critère 1} — {explicite / implicite ; consensus / divergent}
- ...
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 · 140 lines · 54 tokens per session scan A c46d57317334
committee-prep is a skill published in the GitHub repository Ludovic33Fr/product-ai-toolbox (1 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 1,436 once invoked, about $0.0003 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.
Other skills, from other repositories
task-board-setup
Creates a Codex file-based task board. Explicit user invocation only.
tackle-issue
Start-of-work triage in this monorepo. Trigger on: a GitHub issue number ("tackle issue 99", "work on #42", bare #N), pasted proposal/spec text ("investigate this", "pressure-test this", "scope this"), or picker phrasing ("tackle the next issue", "what should I work on"). Read-only investigation that tries to falsify…
stale-proposals
Audit this repository's local proposal queue for stale entries: proposals still marked proposed, deferred, or accepted even though the work already shipped, plus old proposals whose subject has become inert. Reconcile proposals against plugin changelogs and first-parent Git history, automatically resolve only…
add-source
Interactively add a new source to feed-sources.md with type inference, https and name-uniqueness validation, and category checking against feed-categories.md. Appends a formatted row to the Active Sources table. Invoke with /feed-hermit:add-source.
plan-to-tasks
Transform a plancreation planv{N}.md into a structured tasks.yaml + per-WP workpackages/.yaml using parallel Sonnet sub-agents. Use after plan-creation finishes when you need execution-friendly task structure.
debt-ops-add
Register a deferred decision in the tech-debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you…