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.
npx skills add GlamgarOnDiscord/claude-saas-blueprint --skill forkgit clone --depth 1 https://github.com/GlamgarOnDiscord/claude-saas-blueprintWrote 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/skills/glamgarondiscord/claude-saas-blueprint/fork)<a href="https://agentmods.dev/skills/glamgarondiscord/claude-saas-blueprint/fork"><img src="https://agentmods.dev/badge/skills/glamgarondiscord/claude-saas-blueprint/fork/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/skills/glamgarondiscord/claude-saas-blueprint/fork"><img src="https://agentmods.dev/badge/skills/glamgarondiscord/claude-saas-blueprint/fork.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 | $0.00032 | $0.00605 |
| Opus 5 | $0.00016 | $0.00302 |
| Sonnet 5 | $0.00006 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade C, and why
fork scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
1. Supprimer l'historique git du projet original : `rm -rf .git && git init` What it actually says
Arguments
repo: URL GitHub du repo à forker (ou nom court ex: "shadcn/ui")goal: Ce qu'on veut en faire / les modifications à apporter
Instructions
Phase 1 — Évaluer le Repo
Avant de cloner, vérifier via sous-agents :
Agent WebSearch :
- License compatible ? (MIT, Apache = OK, GPL = attention)
- Dernière activité ? (> 6 mois sans commit = risque)
- Stars / forks / issues ouvertes ?
- Stack compatible avec la nôtre ?
Agent WebFetch (README du repo) :
- Quelles features sont déjà implémentées ?
- Quelles sont les dépendances ?
- Comment le setup ?
Phase 2 — Cloner et Explorer
git clone [repo] [nom-projet]- Lancer
/onboardpour scanner le projet cloné - Lancer
/onboardpour comprendre la structure - Identifier les fichiers à modifier vs ceux à garder tel quel
Phase 3 — Plan de Customisation
Via EnterPlanMode, planifier :
## Ce qu'on garde
- [liste des features/fichiers à conserver]
## Ce qu'on modifie
- [feature] → [modification]
- [UI] → [nouveau design]
## Ce qu'on ajoute
- [nouvelle feature]
- [intégration]
## Ce qu'on supprime
- [feature inutile]
- [pages/routes non nécessaires]
Phase 4 — Exécuter
- Supprimer le code inutile d'abord (réduire la surface)
- Rebrander (nom, logo, couleurs, textes)
- Modifier les features existantes
- Ajouter les nouvelles features
- Tester le tout
Phase 5 — Nettoyer
- Supprimer l'historique git du projet original :
rm -rf .git && git init - Mettre à jour le README
- Mettre à jour le
package.json(nom, version, description) - Vérifier les licenses et attributions
/deploy-check
Anti-Patterns
- Ne PAS forker un projet plus complexe que ce qu'on a besoin
- Ne PAS garder du code qu'on ne comprend pas
- Ne PAS ignorer la license
- Préférer les projets avec une architecture propre (plus facile à modifier)
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.
- 11d ago First seen · 72 lines · 32 tokens per session scan C 514570fe7462
fork is a skill published in the GitHub repository GlamgarOnDiscord/claude-saas-blueprint (2 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 605 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
chained-pr
Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.
git-commit
Git commit message generator that creates conventional commit messages based on code changes.
memorix-git-memory
Use when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.