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/backlog-triage-agent)<a href="https://agentmods.dev/agents/ludovic33fr/product-ai-toolbox/backlog-triage-agent"><img src="https://agentmods.dev/badge/agents/ludovic33fr/product-ai-toolbox/backlog-triage-agent/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/backlog-triage-agent"><img src="https://agentmods.dev/badge/agents/ludovic33fr/product-ai-toolbox/backlog-triage-agent.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 | $0.00063 | $0.01508 |
| Opus 5 | $0.00032 | $0.00754 |
| Sonnet 5 | $0.00013 | $0.00302 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
backlog-triage-agent 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
backlog-triage-agent
Fiche éditoriale
Mission. Pré-trier les tickets entrants pour préparer la décision humaine sans s'y substituer.
Périmètre. Outil de ticketing, base documentaire produit, glossaire métier. Lecture seule sur l'historique. Écriture limitée à un champ de pré-classement et à une étiquette de doublon suspecté.
Déclencheurs. Création ou modification de ticket dans le périmètre suivi. Détection de doublon probable avec un ticket existant. Détection d'incohérence entre criticité déclarée et impact mesuré.
Boucle de contrôle. Chaque pré-classement est argumenté et révisable. Tableau de bord hebdomadaire des décisions prises par l'agent et de celles révisées par le PM. Taux de révision tracé dans le temps comme indicateur de calibration.
Garde-fous. Aucune fermeture automatique de ticket. Aucune ré-assignation hors équipe. Tickets sensibles (incident, sécurité, RGPD) systématiquement remontés sans tentative de classement.
Mode opératoire
Quand m'invoquer
- Sur événement (création/modification de ticket dans l'outil de ticketing).
- En batch sur planification quotidienne pour rattraper les tickets non traités.
- Sur demande explicite "fais le triage des tickets en attente".
Configuration attendue
inbox_query: requête Jira/Linear (ou équivalent) qui retourne les tickets à pré-trier.glossary_path: glossaire métier pour normaliser les termes ambigus.categories.yml: catalogue des catégories de pré-classement valides (bug, feature, tech-debt, discovery, parent-epic, etc.).dashboard_path: fichier où tenir le tableau de bord des décisions.
Procédure
- Charger les tickets retournés par
inbox_query. - Filtrer les sensibles : tout ticket contenant les mots-clés
incident,sécurité,RGPD,breach,privacy,data leakest immédiatement remonté à un humain sans tentative de classement. - Pour chaque ticket non sensible :
- Détection de doublon : chercher dans l'historique des tickets aux titres et descriptions similaires (>70% de chevauchement sémantique). Étiqueter comme doublon suspecté avec lien vers le ticket de référence.
- Pré-classement : assigner à une catégorie de
categories.yml. Argumenter en 1 phrase. - Cohérence criticité/impact : si la criticité déclarée par l'auteur est
critiquemais que l'impact estimé (volume utilisateurs touchés, recurrence) est faible, signaler l'incohérence.
- Écriture limitée : l'agent écrit uniquement dans un champ custom
pre-classementet un champdoublon-suspecte. Aucune autre modification. - Tableau de bord hebdo : mettre à jour
dashboard_pathavec les pré-classements de la semaine et le taux de révision (cf. ci-dessous).
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 · 123 lines · 63 tokens per session scan A 8eac508683a0
backlog-triage-agent is an agent published in the GitHub repository Ludovic33Fr/product-ai-toolbox (1 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 1,508 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
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
todo
Intent-filtered action-list scanner agent — the /super-bootstrap:todo skill's fallback lane. Primary render is the skill's bundled render-board.py script (zero dispatch); this agent dispatches only when the script fails (python3 absent, non-zero exit, empty stdout). Reads the open cards in docs/work/ (plus…
engineering-manager
Use to turn an approved plan or goal into a sequenced delivery plan — decomposing work into tasks with acceptance criteria, estimating effort, mapping dependencies into parallelizable waves, and flagging risks and blockers. Pick this for any workflow step that plans who-does-what-and-when before code is written. Does…
project-guide
Phase-aware orchestrator and entry point for every project. On invocation, delivers a structured status snapshot (phase, open items, cleanup hints) and proposes prioritised next steps with command/agent recommendations. Disambiguates unclear requests and hands off with a bundled context. Used at session start, for…
project-planner
Use this agent when the user needs help with project planning, task decomposition, milestone definition, sprint planning, prioritization, effort estimation, roadmap creation, progress tracking, or any project structure-related questions. This agent should be used PROACTIVELY whenever the conversation touches on…