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 agentmods add skills/carbeneai/forge/devteamnpx skills add CarbeneAI/Forge --skill devteamgit clone --depth 1 https://github.com/CarbeneAI/ForgeWhat 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 | $0.00078 | $0.01586 |
| Opus 5 | $0.00039 | $0.00793 |
| Sonnet 5 | $0.00016 | $0.00317 |
| Haiku 4.5 | $0.00008 | $0.00159 |
Grade A, and why
DevTeam 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 2d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevTeam
Security-first autonomous multi-agent software development team with hierarchical coordination through a Project Manager (Joshua), parallel developer agents (Hiram instances), QA engineer (Ezra), security auditor (Nehemiah), and code reviewer (Solomon).
Security Policy: CarbeneAI is a "Security Built In, Not Bolted On" organization. All code produced by DevTeam undergoes mandatory security review by Nehemiah before merge. OWASP Top 10 compliance is required for all web-facing code.
Key Projects:
- carbeneai (carbene.ai) - Parent brand site: open-source tools + training
- cyberdefensetactics (cyberdefensetactics.com) - Security training academy (the product)
- purpleteamops (purpleteamops.app) - Hands-on lab + recurring membership
Workflow Routing
${PAI_DIR}/tools/skill-workflow-notification WorkflowName DevTeam
| Workflow | Trigger | File |
|---|---|---|
| InitProject | "set up dev team", "initialize devteam", "start dev team for [feature]" | workflows/InitProject.md |
| RunTeam | "run the dev team", "start devteam", "execute TODO.md" | workflows/RunTeam.md |
| TeamStatus | "how's the team", "devteam status", "check agent progress" | workflows/TeamStatus.md |
| CollectResults | "collect results", "merge team work", "devteam done" | workflows/CollectResults.md |
Architecture
User (Orchestrator)
└── Joshua (PM) — manages tasks, dispatches agents, monitors progress
├── Hiram-1 (Dev) — implements tasks in git worktrees
├── Hiram-2 (Dev) — implements tasks in parallel
├── Ezra (QA) — writes tests, validates acceptance criteria
├── Nehemiah (Security) — OWASP audit, auth review, vulnerability scan
└── Solomon (Review) — code quality review
Coordination model: Hierarchical through Joshua. No peer-to-peer messaging.
Communication: File-based inbox/outbox in .devteam/agents/ directory.
Task tracking: TODO.md as single source of truth.
Parallelism: Tmux sessions via CodingAgent tools. Git worktrees for isolation.
Security gate: Nehemiah reviews ALL code before merge (mandatory, never skipped).
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- reference/EzraPrompt.md 3.9 KB
- reference/JoshuaPrompt.md 6.3 KB
- reference/MessageProtocol.md 4.5 KB
- reference/TaskFormat.md 4.6 KB
- tools/DevTeamInit.ts 9.4 KB runs code
- tools/MessageBus.ts 12 KB runs code
- tools/TaskBoard.ts 17 KB runs code
- tools/TeamStatus.ts 13 KB runs code
- workflows/CollectResults.md 4.4 KB
- workflows/InitProject.md 3.4 KB
- workflows/RunTeam.md 4.2 KB
- workflows/TeamStatus.md 1.4 KB
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.
- 2d ago First seen · 158 lines · 78 tokens per session scan A 7ff7a4c340e6
DevTeam is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 1,586 once invoked, about $0.0004 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 skills, from other repositories
security-debt-tracker
USAP agent skill for Security Debt Tracking. Use for analyzing aging security findings, computing SLA breach counts, and classifying debt accumulation rate.
task-manager
Capture actionable user requests as persistent tasks, update task status as work progresses, and keep a shared task store in sync. Use when a user asks an agent to do work, check progress, block a task, complete a task, or manage the Kanban board.
implementing-devsecops-security-scanning
Integrates Static Application Security Testing (SAST), Dynamic Application Security Testing (DAST), and Software Composition Analysis (SCA) into CI/CD pipelines using open-source tools. Covers Semgrep for SAST, Trivy for SCA and container scanning, OWASP ZAP for DAST, and Gitleaks for secrets detection. Activates for…
hunt-ato
Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session…
project-manager
Project management expert for Agile, estimation, risk management, and stakeholder communication.
jira
Jira project management expert for issues, sprints, workflows, and reporting.