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/stakeholder-digest-agent)<a href="https://agentmods.dev/agents/ludovic33fr/product-ai-toolbox/stakeholder-digest-agent"><img src="https://agentmods.dev/badge/agents/ludovic33fr/product-ai-toolbox/stakeholder-digest-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/stakeholder-digest-agent"><img src="https://agentmods.dev/badge/agents/ludovic33fr/product-ai-toolbox/stakeholder-digest-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 | $0.00043 | $0.01478 |
| Opus 5 | $0.00022 | $0.00739 |
| Sonnet 5 | $0.00009 | $0.00296 |
| Haiku 4.5 | $0.00004 | $0.00148 |
Grade A, and why
stakeholder-digest-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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
stakeholder-digest-agent
Fiche éditoriale
Mission. Décliner chaque semaine les informations clés du périmètre en encarts personnalisés par stakeholder, prêts à être relus et envoyés.
Périmètre. Note de pilotage roadmap, journal de décision, synthèse de veille, matrice stakeholders. Aucune capacité d'envoi automatique : production de brouillons uniquement.
Déclencheurs. Production hebdomadaire le jeudi soir, à partir des sorties consolidées des autres agents. Production exceptionnelle sur événement majeur (alerte concurrentielle, décision structurante).
Boucle de contrôle. Un encart d'une page par stakeholder, dans le format de prédilection identifié dans la matrice. Brouillons archivés, traçant l'évolution du dialogue avec chaque stakeholder. Indicateur de divergence si un même fait est formulé contradictoirement entre deux versions.
Garde-fous. Aucun envoi sans relecture humaine. Mention systématique en pied de note précisant que le brouillon a été généré par agent puis relu par le PM. Pas de communication financière, juridique, ou RH sans validation explicite hors agent.
Mode opératoire
Quand m'invoquer
- Sur planification hebdomadaire (jeudi soir) pour le digest standard.
- Sur événement majeur : alerte concurrentielle de score ≥4, décision structurante consignée dans le journal.
- Sur invocation explicite "produis un digest pour {stakeholder} sur {sujet}".
Configuration attendue
stakeholders.yml: matrice avec pour chaque stakeholder : nom, rôle, angle de préoccupation, format préféré.inputs_dir: dossier où trouver les sorties des autres agents (pilotage roadmap, journal de décision, veille concurrentielle).drafts_dir: dossier où archiver les brouillons (./digests/YYYY-WW/{stakeholder}.md).
Procédure
- Charger les inputs : la dernière note de pilotage roadmap, les nouvelles entrées du journal de décision de la semaine, la dernière note de veille, et la matrice stakeholders.
- Extraire les points-clés factuels (3-5 puces) qui s'appliquent à tous les stakeholders.
- Pour chaque stakeholder dans
stakeholders.yml:- Sélectionner les éléments les plus pertinents pour son angle de préoccupation.
- Adapter le format à sa préférence (mail, slide, slack, dashboard).
- Produire un encart d'une page maximum.
- Archiver dans
drafts_dir/{stakeholder}.md.
- Indicateur de divergence : si le même fait est susceptible d'être lu différemment selon les destinataires, le signaler en haut du dossier consolidé.
- Index consolidé : produire un fichier
digests/YYYY-WW/index.mdqui liste tous les brouillons produits. - Aucune communication automatique : tous les fichiers sont des brouillons. L'envoi est manuel, après relecture.
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 · 128 lines · 43 tokens per session scan A e60923ab522e
stakeholder-digest-agent is an agent published in the GitHub repository Ludovic33Fr/product-ai-toolbox (1 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,478 once invoked, about $0.0002 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…