agentmods.dev

weak-signals-watcher

weak-signals-watcher is an agent for Claude Code from Ludovic33Fr/product-ai-toolbox. It costs 54 tokens per session (1,520 once invoked), scanned A, original, MIT.

An agent that continuously looks for early signs of changing user needs in support tickets, user quotes, public mentions, forums, and structured sales feedback. It records those signals for product discovery, the process of learning what users need.

In plain words
What is it for?
Use it for daily source polling, detecting new or diverging themes, recording each signal and its source, and producing a weekly discovery summary without contacting users.
Why use it?
It helps teams notice emerging themes or gaps between what users say and how they use a product before those patterns become obvious in standard metrics.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the pm-augmente plugin — 12 skills, 6 agents shipped together

not rated 1repo 4mo ago A scan 54 tokens original MIT

Good fit Use it for daily source polling, detecting new or diverging themes, recording each signal and its source, and producing a weekly discovery summary without contacting users.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ludovic33fr/product-ai-toolbox/weak-signals-watcher
View source ↗ Ludovic33Fr/product-ai-toolbox
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/Ludovic33Fr/product-ai-toolbox

Made for: Claude Code.

Or install pm-augmente, the plugin that ships this one along with the rest of its 12 skills, 6 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 weak-signals-watcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/ludovic33fr/product-ai-toolbox/weak-signals-watcher/github.svg)](https://agentmods.dev/agents/ludovic33fr/product-ai-toolbox/weak-signals-watcher)
Your own site
<a href="https://agentmods.dev/agents/ludovic33fr/product-ai-toolbox/weak-signals-watcher"><img src="https://agentmods.dev/badge/agents/ludovic33fr/product-ai-toolbox/weak-signals-watcher/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.

agentmods 80×15 button for weak-signals-watcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/ludovic33fr/product-ai-toolbox/weak-signals-watcher"><img src="https://agentmods.dev/badge/agents/ludovic33fr/product-ai-toolbox/weak-signals-watcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,520 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 $0.00054 $0.01520
Opus 5 $0.00027 $0.00760
Sonnet 5 $0.00011 $0.00304
Haiku 4.5 $0.00005 $0.00152

Measured 11d ago against content hash 59e2d414ff5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

weak-signals-watcher 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.

agents/weak-signals-watcher.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

weak-signals-watcher

Fiche éditoriale

Mission. Détecter en continu les signaux faibles utilisateurs (verbatims, support, mentions externes) et alimenter le journal de discovery.

Périmètre. Verbatims utilisateurs, tickets support, mentions sur réseaux sociaux et forums publics, retours commerciaux structurés. Pas d'accès aux données nominatives non anonymisées.

Déclencheurs. Polling quotidien des sources. Détection d'émergence (occurrence soudaine d'un thème nouveau). Détection de divergence (écart entre verbatims et indicateurs d'usage).

Boucle de contrôle. Trace de chaque signal détecté et de la source d'origine. Distinction explicite entre signal validé et signal hypothétique. Synthèse hebdomadaire alignée sur le format du skill weak-signals-weekly.

Garde-fous. Anonymisation systématique des verbatims dans les sorties. Aucune action sortante vers les utilisateurs. Revue trimestrielle des thèmes ignorés par l'agent pour détecter ses angles morts.

Mode opératoire

Quand m'invoquer

  • Sur planification quotidienne pour la détection en continu (voir « Mise en routine »).
  • Sur invocation explicite pour produire une synthèse hebdomadaire ou un point ad hoc.
  • Sur demande de revue trimestrielle des angles morts.

Configuration attendue

Avant la première exécution, l'utilisateur fournit :

  • sources.yml : sources surveillées (verbatims, support, mentions, retours commerciaux), avec leur type d'accès.
  • journal_path : dossier où archiver les détections quotidiennes (./journal-discovery/YYYY-MM-DD.md).
  • weekly_path : fichier où produire la note hebdomadaire (./journal-discovery/weekly/YYYY-WW.md).
  • usage_metrics_path (optionnel) : tableau d'indicateurs d'usage agrégés pour la détection de divergence.

Procédure

  1. Polling quotidien. Charger les nouvelles entrées des sources depuis la dernière exécution. Anonymiser tout verbatim contenant un identifiant utilisateur, un email ou un nom.
  2. Détection d'émergence. Comparer la fréquence des termes/thèmes de la journée à la moyenne mobile sur 4 semaines. Marquer les pics statistiques (>2 écarts-types) comme signaux émergents.
  3. Détection de divergence. Si usage_metrics_path est fourni : comparer le volume de mentions d'une feature et son indicateur d'usage. Toute mention forte couplée à un usage faible (ou inverse) est consignée en signal.
  4. Classification. Pour chaque signal : signal validé (≥3 occurrences distinctes, sources hétérogènes) ou hypothétique (1-2 occurrences ou source unique).
  5. Archivage quotidien. Écrire la liste des signaux du jour dans journal_path du jour, format compact (cf. ci-dessous).
  6. Synthèse hebdomadaire. Le lundi matin, agréger les signaux de la semaine écoulée et produire une note dans weekly_path au format weak-signals-weekly.

Read the full file on GitHub · 126 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. 11d ago First seen · 126 lines · 54 tokens per session scan A 59e2d414ff5b

Subscribe to this mod's changes

weak-signals-watcher is an agent 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 1,520 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.

Claude CodeMarketing and SEOResearchai-agentsanthropicclaudeclaude-code-agentsclaude-code-plugindiscoverywatcherweak-signalsweekly
Related

Other agents, from other repositories

skill-creator

Creates and improves Claude Code skills. Triggers: create skill, improve skill, fix activation.

kochetkov-ma/claude-brewcode · 23 tokens

bc-rules-organizer

Internal. Spawned only by /brewcode:rules. No direct/auto use.

kochetkov-ma/claude-brewcode · 24 tokens

ssh-admin

Linux server admin: SSH, Docker, systemd, Nginx, SSL. Triggers: ssh admin, server management.

kochetkov-ma/claude-brewcode · 29 tokens

text-optimizer

Optimizes text/docs for LLM token efficiency. Triggers: optimize prompt, reduce tokens, compress.

kochetkov-ma/claude-brewcode · 25 tokens

bash-expert

Creates sh/bash scripts for Mac/Linux. Triggers: create script, bash script, shell script.

kochetkov-ma/claude-brewcode · 24 tokens

agent-creator

Creates and improves Claude Code agents. Triggers: create agent, improve agent, scaffold agent.

kochetkov-ma/claude-brewcode · 23 tokens