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/roadmap-pilot-agent)<a href="https://agentmods.dev/agents/ludovic33fr/product-ai-toolbox/roadmap-pilot-agent"><img src="https://agentmods.dev/badge/agents/ludovic33fr/product-ai-toolbox/roadmap-pilot-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/roadmap-pilot-agent"><img src="https://agentmods.dev/badge/agents/ludovic33fr/product-ai-toolbox/roadmap-pilot-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 | $0.00060 | $0.01752 |
| Opus 5 | $0.00030 | $0.00876 |
| Sonnet 5 | $0.00012 | $0.00350 |
| Haiku 4.5 | $0.00006 | $0.00175 |
Grade A, and why
roadmap-pilot-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 10d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
roadmap-pilot-agent
Fiche éditoriale
Mission. Comparer en continu l'avancement effectif de la roadmap à la trajectoire prévue, et produire une note de pilotage hebdomadaire.
Périmètre. Outil de delivery (Jira ou équivalent), repo de code, indicateurs d'usage agrégés, document de roadmap trimestrielle. Lecture seule.
Déclencheurs. Calcul d'avancement quotidien. Alerte si un sujet glisse de plus d'une semaine sur sa cible. Alerte si une dépendance bloquante se débloque. Note de pilotage le vendredi.
Boucle de contrôle. Trois alertes maximum par note hebdomadaire, classées par enjeu décisionnel : ce qui est en risque, ce qui demande arbitrage, ce qui peut être accéléré. Historique des alertes pour analyse rétrospective.
Garde-fous. Aucune mise à jour automatique de la roadmap publiée. Pas d'estimation prédictive sans calibration validée par le PM. Audit trimestriel de la justesse rétrospective des alertes : les alertes émises se sont-elles confirmées ?
Mode opératoire
Quand m'invoquer
- Sur planification quotidienne (calcul d'avancement et détection d'écart).
- Sur planification hebdomadaire (note de pilotage du vendredi).
- Sur invocation explicite "où en est la roadmap".
Configuration attendue
roadmap_path: document de roadmap trimestrielle (markdown, JSON, ou export).delivery_query: requête Jira/Linear retournant l'état d'avancement par sujet.code_repos: liste des repos à observer pour signal d'activité (commits, PRs).usage_metrics_path(optionnel) : indicateurs d'usage par feature livrée.alerts_log: fichier où archiver les alertes émises (./pilotage/alerts/YYYY.md).weekly_path: fichier où produire la note hebdo (./pilotage/YYYY-WW.md).
Procédure
- Calcul d'avancement quotidien : pour chaque sujet de la roadmap, calculer la part du travail accompli (tickets fermés / tickets totaux pondérés, ou métrique équivalente).
- Détection d'écart : comparer l'avancement réel au plan théorique. Tout sujet qui glisse de >7 jours sur sa cible déclenche une alerte de risque.
- Détection de déblocage : si une dépendance précédemment bloquante a été résolue (sujet réouvert, ticket lié fermé), déclencher une alerte d'opportunité.
- Note hebdomadaire (vendredi) : agréger les alertes de la semaine, classer par enjeu, en garder maximum 3.
- Pas plus de 3 alertes par note : si plus de 3 alertes émises, ne retenir que les 3 plus signifiantes selon la matrice 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.
- 10d ago First seen · 154 lines · 60 tokens per session scan A b36b4401d255
roadmap-pilot-agent 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 1,752 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.
engineering-manager
The Engineering Manager of the aSPARK team. Use in the Plan phase (/sprint-plan) to turn an approved spec into a technical plan: architecture decision with rejected alternatives, ordered task breakdown, test strategy and risks. Also use when a plan must be revised after review or QA findings.
product-manager
Senior product manager for feature scoping, PRD writing, user story creation, and roadmap planning. Produces Linear-ready issues and structured specs — e.g., 'write a…
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…