roadmap-variants

roadmap-variants is a skill for Claude Code from Ludovic33Fr/product-ai-toolbox. It costs 53 tokens per session (1,710 once invoked), scanned A, original, MIT.

A roadmap planning tool that creates three versions of a product roadmap: cautious, aggressive, and balanced. A roadmap is a planned order of work, while an OKR is a goal paired with measurable results.

In plain words
What is it for?
Use it during quarterly roadmap reviews with the current roadmap, team constraints, and target OKR to compare alternative plans line by line.
Why use it?
It helps teams compare how different assumptions about capacity, dependencies, and risk affect their quarterly plan.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit Use it during quarterly roadmap reviews with the current roadmap, team constraints, and target OKR to compare alternative plans line by line.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ludovic33fr/product-ai-toolbox/roadmap-variants
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.

Any agent
npx skills add Ludovic33Fr/product-ai-toolbox --skill roadmap-variants
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 roadmap-variants

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ludovic33fr/product-ai-toolbox/roadmap-variants"><img src="https://agentmods.dev/badge/skills/ludovic33fr/product-ai-toolbox/roadmap-variants.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,710 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 $0.00053 $0.01710
Opus 5 $0.00026 $0.00855
Sonnet 5 $0.00011 $0.00342
Haiku 4.5 $0.00005 $0.00171

Measured 11d ago against content hash b5d68aa9d494, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

roadmap-variants 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.

skills/roadmap-variants/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

roadmap-variants

Fiche éditoriale

Objectif. Simuler trois variantes d'une roadmap selon des hypothèses de capacité et de risque.

Entrées. Roadmap actuelle, contraintes équipe, OKR cible.

Sorties. Variante prudente, variante agressive, variante équilibrée, comparées ligne à ligne.

Cadence d'usage. À chaque révision trimestrielle de roadmap.

Mode opératoire

Quand m'invoquer

L'utilisateur prépare une révision trimestrielle et veut tester des scénarios avant de figer la version finale. Il me fournit la roadmap actuelle (liste de sujets avec ordre et estimation rough), les contraintes équipe (capacité, congés, dépendances tech), et l'OKR cible.

Procédure

  1. Reformuler les hypothèses explicites de la roadmap actuelle (capacité supposée, ordre, dépendances assumées).
  2. Identifier 2-3 leviers sur lesquels les variantes vont diverger : ordre des sujets, périmètre par sujet, parallélisation, coupe d'un sujet, ajout d'un sujet.
  3. Construire la variante prudente : maximise les chances de tenir l'OKR à minima ; coupe le périmètre ambigu ; ne dépend de personne d'externe ; ne prend aucun risque tech non maîtrisé.
  4. Construire la variante agressive : maximise l'impact si tout se passe bien ; assume des dépendances externes ; tente plus de sujets en parallèle ; accepte un risque de glissement si gain potentiel ≥ 2x.
  5. Construire la variante équilibrée : posture par défaut ; arbitre entre les deux extrêmes ; couvre l'OKR avec marge réaliste.
  6. Tableau comparatif ligne à ligne : un sujet par ligne, statut dans chaque variante (gardé / coupé / réduit / ajouté), ordre de priorité, risque associé.
  7. Recommandation argumentée : laquelle des trois est la posture par défaut, et sous quelle condition basculer vers prudente ou agressive.

Format de sortie

# Roadmap — variantes pour {trimestre}

## OKR cible
{rappel de l'OKR}

## Hypothèses de capacité
- Effectif : {n} ETP
- Capacité produit-tech : ~{x} jours-homme sur le trimestre
- Risques connus : ...

## Leviers de différenciation des variantes
1. {levier 1}
2. {levier 2}
3. {levier 3}

## Tableau comparatif

| Sujet | Prudente | Équilibrée | Agressive | Risque associé |
|-------|----------|------------|-----------|----------------|
| {sujet 1} | gardé (P1) | gardé (P1) | gardé (P1) + scope étendu | ... |
| {sujet 2} | coupé | gardé (P2) | gardé (P1) en parallèle | dépendance équipe X |
| {sujet 3} | ... | ... | ... | ... |

## Variante prudente — {nom court}

**Périmètre** : ...
**Charge estimée** : {x}% de la capacité
**Probabilité de tenir l'OKR** : haute
**Probabilité de dépasser l'OKR** : faible
**Risques principaux** : ...

## Variante équilibrée — {nom court}

**Périmètre** : ...
**Charge estimée** : {x}% de la capacité
**Probabilité de tenir l'OKR** : moyenne-haute
**Probabilité de dépasser l'OKR** : moyenne
**Risques principaux** : ...

## Variante agressive — {nom court}

**Périmètre** : ...
**Charge estimée** : {x}% de la capacité (risque de saturation)
**Probabilité de tenir l'OKR** : moyenne
**Probabilité de dépasser l'OKR** : haute si tout va bien
**Risques principaux** : ...

## Recommandation

**Posture par défaut : {variante}.**

{2-3 phrases qui justifient.}

**Bascule vers prudente si** : {condition factuelle observable}
**Bascule vers agressive si** : {condition factuelle observable}

Read the full file on GitHub · 150 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 · 150 lines · 53 tokens per session scan A b5d68aa9d494

Subscribe to this mod's changes

roadmap-variants is a skill published in the GitHub repository Ludovic33Fr/product-ai-toolbox (1 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 1,710 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.

Related

Other skills, from other repositories

task-board-setup

Creates a Codex file-based task board. Explicit user invocation only.

kochetkov-ma/claude-brewcode · 19 tokens

tackle-issue

Start-of-work triage in this monorepo. Trigger on: a GitHub issue number ("tackle issue 99", "work on #42", bare #N), pasted proposal/spec text ("investigate this", "pressure-test this", "scope this"), or picker phrasing ("tackle the next issue", "what should I work on"). Read-only investigation that tries to falsify…

gtapps/claude-code-hermit · 149 tokens

stale-proposals

Audit this repository's local proposal queue for stale entries: proposals still marked proposed, deferred, or accepted even though the work already shipped, plus old proposals whose subject has become inert. Reconcile proposals against plugin changelogs and first-parent Git history, automatically resolve only…

gtapps/claude-code-hermit · 140 tokens

add-source

Interactively add a new source to feed-sources.md with type inference, https and name-uniqueness validation, and category checking against feed-categories.md. Appends a formatted row to the Active Sources table. Invoke with /feed-hermit:add-source.

gtapps/claude-code-hermit · 56 tokens

plan-to-tasks

Transform a plancreation planv{N}.md into a structured tasks.yaml + per-WP workpackages/.yaml using parallel Sonnet sub-agents. Use after plan-creation finishes when you need execution-friendly task structure.

QBall-Inc/the-bulwark · 50 tokens

debt-ops-add

Register a deferred decision in the tech-debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you…

bcanfield/agentic-tech-debt · 115 tokens