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 weak-signals-weeklygit 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/weak-signals-weekly)<a href="https://agentmods.dev/skills/ludovic33fr/product-ai-toolbox/weak-signals-weekly"><img src="https://agentmods.dev/badge/skills/ludovic33fr/product-ai-toolbox/weak-signals-weekly/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/weak-signals-weekly"><img src="https://agentmods.dev/badge/skills/ludovic33fr/product-ai-toolbox/weak-signals-weekly.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 | $0.00057 | $0.01302 |
| Opus 5 | $0.00028 | $0.00651 |
| Sonnet 5 | $0.00011 | $0.00260 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
weak-signals-weekly 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 12d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
weak-signals-weekly
Fiche éditoriale
Objectif. Produire la synthèse hebdomadaire de signaux faibles à partir de sources multiples (verbatims, logs, mentions, support).
Entrées. Connecteurs vers les sources brutes, période d'observation, contexte stratégique du périmètre.
Sorties. Synthèse markdown structurée en quatre blocs (thèmes émergents, signaux faibles, anomalies, questions ouvertes), lisible en cinq minutes.
Cadence d'usage. Chaque lundi matin, en automatique.
Mode opératoire
Quand m'invoquer
L'utilisateur me demande la synthèse hebdo de signaux faibles, ou évoque un besoin d'observation utilisateur sur la semaine. Sources typiques : exports de verbatims (CSV ou markdown), tickets support, mentions externes (forums, social), logs d'usage agrégés.
Procédure
- Identifier la fenêtre d'observation (par défaut : 7 derniers jours ; ajustable).
- Charger les sources fournies. Si une source est inaccessible ou vide, le signaler dans la note.
- Catégoriser chaque entrée dans l'un des 4 blocs : thème émergent (récurrent et nouveau), signal faible (rare mais inattendu), anomalie (écart entre data et verbatims), question ouverte (chose à creuser).
- Anonymiser systématiquement : pas de nom, pas d'identifiant utilisateur, pas d'email.
- Sourcer chaque entrée : lien ou référence à la source d'origine, date, et indice de confiance (faible / moyenne / forte selon le nombre d'occurrences).
- Distinguer fait et hypothèse : un fait observé est repérable dans les sources ; une hypothèse interprétative est une lecture du PM, à signaler comme telle.
- Produire la note au format ci-dessous.
Format de sortie
# Signaux faibles — semaine du {date_debut} au {date_fin}
## Thèmes émergents
- {thème} — observé dans {n} verbatims / {m} tickets — confiance {faible|moyenne|forte}
Sources : [{ref}], [{ref}]
- ...
## Signaux faibles
- {signal} — apparu pour la première fois cette semaine — confiance faible
Source : [{ref}]
- ...
## Anomalies
- {description du gap} — confiance {niveau}
Indicateur d'usage : {chiffre}
Verbatim contradictoire : "{citation anonymisée}" — [{ref}]
- ...
## Questions ouvertes
- ?
- ?
## Sources consultées
{nombre} sources sur {total}, {nombre_indispo} indisponibles ou vides.
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.
- 12d ago First seen · 114 lines · 57 tokens per session scan A 412105b955d9
weak-signals-weekly is a skill published in the GitHub repository Ludovic33Fr/product-ai-toolbox (1 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 1,302 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
semble-setup
Project setup tools for semblecode semantic code search. Semantic search finds code by meaning or concept, rather than only matching exact words.
text-optimize
Optimizes text/docs for LLM token efficiency. Triggers - optimize, reduce tokens, compress, deep compress.
context-slim
A tool for shortening the instructions and saved information that an AI coding agent loads into its context, the text it uses to decide what to do.
md-to-pdf
Convert Markdown to PDF via reportlab or weasyprint engines. Triggers - pdf, md to pdf, markdown to pdf, generate pdf.
publish
A tool for publishing text, Markdown files, or websites to brewpage.app and receiving a web address for the published result.
agents
Creates, improves, syncs Codex subagents. Triggers: create agent, improve agent, sync agents, memory sync.