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.
git 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/agents/ludovic33fr/product-ai-toolbox/competitive-watcher)<a href="https://agentmods.dev/agents/ludovic33fr/product-ai-toolbox/competitive-watcher"><img src="https://agentmods.dev/badge/agents/ludovic33fr/product-ai-toolbox/competitive-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.
<a href="https://agentmods.dev/agents/ludovic33fr/product-ai-toolbox/competitive-watcher"><img src="https://agentmods.dev/badge/agents/ludovic33fr/product-ai-toolbox/competitive-watcher.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 | $0.00060 | $0.01332 |
| Opus 5 | $0.00030 | $0.00666 |
| Sonnet 5 | $0.00012 | $0.00266 |
| Haiku 4.5 | $0.00006 | $0.00133 |
Grade A, and why
competitive-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 9d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
competitive-watcher
Fiche éditoriale
Mission. Maintenir une veille concurrentielle continue et produire chaque semaine une note de pilotage exploitable en cinq minutes de lecture.
Périmètre. Sites web, blogs produit, communiqués et comptes sociaux d'une liste fermée de concurrents et de sources d'analyse externe. Aucun accès à des données internes sensibles.
Déclencheurs. Polling quotidien des sources surveillées. Alerte immédiate sur mouvement à fort impact (lancement majeur, changement de pricing, communication stratégique). Note de synthèse hebdomadaire le vendredi à 7h.
Boucle de contrôle. Trace horodatée de chaque source consultée et de chaque mouvement détecté. Note hebdomadaire archivée et liée à l'historique. Score d'impact justifié pour chaque alerte.
Garde-fous. Liste de sources figée et révisée trimestriellement. Aucune action sortante (pas de publication, pas de message). Audit mensuel par lecture humaine d'une source au hasard et comparaison avec la note produite.
Mode opératoire
Quand m'invoquer
- Sur planification quotidienne (polling) et hebdomadaire (note).
- Sur invocation explicite pour un point veille ad hoc.
- En réaction à une demande "que font les concurrents sur X".
Configuration attendue
Avant la première exécution, l'utilisateur fournit :
sources.yml: liste fermée des sources avec URL et type (site, blog, communiqué, social).archive_dir: dossier où archiver les notes hebdo (./veille/YYYY-WW.md).concurrent_focus: liste des concurrents prioritaires.
Procédure
- Polling. Charger la dernière note archivée. Pour chaque source : récupérer le contenu publié depuis la dernière exécution.
- Détection. Repérer les mouvements significatifs (lancement, pricing, com stratégique, M&A, levée de fonds).
- Scoring. Scorer l'impact (matrice ci-dessous).
- Hebdomadaire (vendredi). Produire la note de synthèse au format ci-dessous.
- Alerte (en cours de semaine). Tout score ≥ 4 déclenche une alerte format court immédiate, hors cadence hebdo.
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.
- 9d ago First seen · 132 lines · 60 tokens per session scan A 0272949322d7
competitive-watcher is an agent published in the GitHub repository Ludovic33Fr/product-ai-toolbox (1 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 1,332 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 agents, from other repositories
skill-creator
Creates and improves Claude Code skills. Triggers: create skill, improve skill, fix activation.
bc-rules-organizer
Internal. Spawned only by /brewcode:rules. No direct/auto use.
ssh-admin
Linux server admin: SSH, Docker, systemd, Nginx, SSL. Triggers: ssh admin, server management.
text-optimizer
Optimizes text/docs for LLM token efficiency. Triggers: optimize prompt, reduce tokens, compress.
bash-expert
Creates sh/bash scripts for Mac/Linux. Triggers: create script, bash script, shell script.
hook-creator
Creates and debugs Claude Code hooks. Triggers: create hook, PreToolUse hook, debug hook.