Chalk Labs
Need help deploying tollfree-agent-matrix?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/digitaleflex-tollfree-agent-matrix
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
tollfree-agent-matrix- Description
- None
- License
- MIT
- Instructions
- 281 lines in SKILL.md · view on GitHub
Before installing
- Instructions read files in your home folder (~/.ssh, ~/.aws…)
Agent Skills spec issues
- invalid YAML frontmatter: Nested mappings are not allowed in compact mappings at line 2, column 14:
- name: missing
- description: missing
Files (1)
- SKILL.md
SKILL.md (first lines)
# Matrice HASH_AGENT_MATRIX — Équipe HASH Engineering
Cette matrice définit **quelle équipe d'agents** déclencher selon le **type de tâche**, son **niveau de risque**, et le **pipeline optimal**. Elle est utilisée par le routage intelligent (AGENTS.md) et par le superviseur `tollfree`.
---
## 🎯 Agents Principaux (2)
| Agent | Modèle | Rôle | Activation |
|---|---|---|---|
| `@planner` | `google/gemini-2.5-flash` (FREE) | Transforme une demande en plan validé. Ne code jamais. | L2, L3, L4 |
| `@builder` | `google/gemini-2.5-flash` (FREE) | Exécute les plans, implémente, corrige, refactorise. | L1, L2, L3, L4 |
> **Règle** : `@planner` + `@builder` sont les seuls agents principaux. Les autres sont des sous-agents spécialisés appelés à la demande.
---
## 🧠 Sous-Agents Spécialisés (7)
| Agent | Modèle | Rôle | Trigger automatique | Permissions |
|---|---|---|---|---|
| `@architect` | `google/gemini-2.5-flash` | Décisions architecturales, modularité, dette technique | L3, L4, nouveau module, refonte API | `bash: deny`, `edit: deny` |
| `@design-lead` | `google/gemini-2.5-flash` | Direction visuelle, UX, design system, accessibilité | UI majeure, nouveau produit, dashboard | `bash: allow`, `edit: allow` |
| `@quality-engineer` | `google/gemini-2.5-flash` | Détecte sur-ingénierie, code IA suspect, non-maintenable | L2, L3, L4, avant commit | `bash: deny`, `edit: deny` |
| `@tester` | `google/gemini-2.5-flash` | Tests ciblés, validation fonctionnelle, régressions | Après tout code non-trivial | `bash: allow`, `edit: deny` |
| `@security` | `google/gemini-2.5-flash` | Auth, authz, input validation, secrets, config | Auth, payments, API, production | `bash: deny`, `edit: deny` |
| `@reviewer` | `google/gemini-2.5-flash` | Revue indépendante : bugs, sécurité, qualité, cohérence | Avant merge, L2-L4 | `bash: deny`, `edit: deny` |
| `@git-engineer` | `google/gemini-2.5-flash` | Git, commits, PR, CI/CD, repo hygiene | Merge prep, pipeline CI | `bash: allow`, `edit: deny` |
> **Tous les modèles sont FREE** (`google/gemini-2.5-flash` ou équivalents).
---
## 🎨 Pipeline par Niveau de Risque (Matrice de Routage)
### L1 — Simple (typo, config, bug localisé, couleur)
```
@builder (L1)
↓
✅ SHIP (vérif basique)
```
| Agent | Skills | Validation |
|---|---|---|
| `@builder` | `tollfree-verification`, `tollfree-enterprise-development` | Smoke test rapide |
---
### L2 — Moyen (feature limitée, module, endpoint, business logic)
```
@planner
↓
@builder
↓
@tester (ciblé)
↓
@quality-engineer (code smell check)
↓
@reviewer (independant)
↓
✅ SHIP / ❌ FIX
```
| Agent | Skills | Validation |
|---|---|---|
| `@planner` | `writing-plans`, `tollfree-code-navigation` | Plan approuvé par utilisateur |
| `@builder` | `tollfree-enterprise-development`, `tollfree-verification` | - |
| `@tester` | `tollfree-verification` | Tests ciblés uniquement |
| `@quality-engineer` | `tollfree-enterprise-development`, `simplify` | Quality report |
| `@reviewer` | `code-review-skill`, `tollfree-verification` | SHIP/FIX |
---
### L3 — Complexe (nouveau module, architecture, API change, auth, payment)
```
@planner
↓
@architect (décision + alternatives)
↓
⚠️ USER APPROVAL REQUIRED
↓
@builder
↓
@security (si zone sensible)
↓
@tester (module + consumers)
↓
@quality-engineer
↓
@reviewer (indépendant)
↓
✅ SHIP / ❌ FIX
```
| Agent | Skills | Validation |
|---|---|---|
| `@planner` | `writing-plans`, `tollfree-code-navigation` | Plan + risques identifiés |
| `@architect` | `writing-plans` (architecture), `tollfree-enterprise-development` | Décision architecturale documentée |
| `@builder` | `tollfree-enterprise-development`, `tollfree-verification` | - |
| `@security` | `tollfree-enterprise-development`, `cybersecurity` | Security audit |
| `@tester` | `tollfree-verification` | Tests module + consumers |
| `@quality-engineer` | `tollfree-enterprise-development`, `simplify` | Quality report |
| `@reviewer` | `code-review-skill`, `tollfree-verification` | SHIP/FIX |
---
### L4 — Critique (production, données sensibles, migration destructive, infra)
```
@planner
↓
@architect (risk assessment complet)
↓
⚠️ USER APPROVAL REQUISE (écrite)
↓
@security (audit approfondi)
↓
@builder (exécution protégée)
↓
@tester (exhaustif : module + intégration + edge cases)From digitaleflex/eurinhash-opencode-booster, MIT.
More from digitaleflex/eurinhash-opencode-booster
- 0.559score
tollfree-code-navigation
digitaleflex
Use when exploring unfamiliar code, locating files or symbols, or understanding dependencies before editing.
SkillAFreshness: AClaude Code +9 - 0.559score
tollfree-enterprise-development
digitaleflex
Use when writing or reviewing production code.
SkillAFreshness: AClaude Code +9 - 0.521score
12ui-design
digitaleflex
REQUIRED for all non-trivial UI creation.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 2
- Open issues
- 64
- Last commit (this folder)
- Oct 23, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from digitaleflex
- 0.559score
tollfree-code-navigation
digitaleflex
Use when exploring unfamiliar code, locating files or symbols, or understanding dependencies before editing.
SkillAFreshness: AClaude Code +9 - 0.559score
tollfree-enterprise-development
digitaleflex
Use when writing or reviewing production code.
SkillAFreshness: AClaude Code +9 - 0.521score
12ui-design
digitaleflex
REQUIRED for all non-trivial UI creation.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get tollfree-agent-matrix running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
tollfree-agent-matrix skill. Agent Mart. https://agentmart.dev/skills/digitaleflex-tollfree-agent-matrix (last updated 2026-10-24)