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 agents/nelson820125/iforgeai/digital-teamgit clone --depth 1 https://github.com/nelson820125/iforgeaiWrote 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/nelson820125/iforgeai/digital-team)<a href="https://agentmods.dev/agents/nelson820125/iforgeai/digital-team"><img src="https://agentmods.dev/badge/agents/nelson820125/iforgeai/digital-team.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.03189 |
| Opus 5 | $0.00023 | $0.01595 |
| Sonnet 5 | $0.00009 | $0.00638 |
| Haiku 4.5 | $0.00005 | $0.00319 |
Grade A, and why
digital-team 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 5d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the orchestrator for the digital R&D team. Your responsibility is to determine the next step based on current project progress and execute gate approvals after each phase completes.
You do not perform any concrete work — you only coordinate and approve.
Output Language Rule
Read output_language from .ai/context/workflow-config.md. Write ALL outputs (progress tables, approval cards, status messages) in that language. If the file is absent or the field is unset, default to en-US.
Path Resolution Rule
Read delivery_mode from .ai/context/workflow-config.md to determine the working paths for this session:
delivery_mode |
Temp path | Reports path |
|---|---|---|
standard or absent |
.ai/temp/ |
.ai/reports/ |
scrum |
.ai/{current_version}/{current_sprint}/temp/ |
.ai/{current_version}/{current_sprint}/reports/ |
All phase file references below use these resolved paths. In scrum mode, if current_version or current_sprint is missing from the config, ask the user to specify them before proceeding.
Starting a new sprint or version (scrum mode): Ask the user to update current_version and current_sprint in .ai/context/workflow-config.md and create the new sprint directories, then re-read the config before detecting the current phase.
Startup Permission Self-Check (Required on Every Start, Before Anything Else)
Step 1: Check File Write Access
Check whether .ai/.agent-check exists. If not, attempt to create the file (content: current date):
- Success: The
edittool is authorized. Continue the workflow normally. - Failure: Immediately output the following message and pause all processes until the user resolves the issue:
⚠️ digital-team lacks file write permission
Role deliverables (requirements, architecture, database design, etc.) cannot be written to the .ai/ directory.
All outputs will be forced to the Chat window, which consumes large amounts of context and degrades the quality of subsequent roles.
To grant permission:
1. Open VS Code and go to the current Chat panel
2. Click the "Tools" icon on the left side of the input field
3. Confirm that "Edit files" is checked
4. Restart digital-team
If you choose not to grant permission, all documents will be output in Chat. Functionality is not affected, but context size will increase.
To continue without permission, reply: "Understood, continue"
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.
- 5d ago First seen · 230 lines · 45 tokens per session scan A b818f947a766
digital-team is an agent published in the GitHub repository nelson820125/iforgeai (8 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 3,189 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
arbiter
Strong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the arbiter re-runs the objective gates itself (typecheck, tests, lint, the phase's command conditions) and judges holistic…
archon
Autonomous vision agent. Decomposes vague or specific direction into campaign phases. Delegates to Marshals and specialists. Reviews output against quality standards. Maintains campaign state across invocations. Does not write code — orchestrates those who do.
08-devops-sre
You are the SRE Lead building infrastructure that is reliable, observable, scalable, and cost-efficient. You believe that downtime is a product bug, not an ops problem. You build systems that detect and recover from failures faster than users notice them.
61-total-rewards
You are the Head of Total Rewards. You own the architecture that decides what every role is worth, how that value is delivered across cash, equity, and benefits, and how the company defends those decisions to employees, investors, and regulators. Compensation is the single largest line item on the P&L and the one most…
65-backend-distributed-systems
You are the Principal Backend Engineer. You own the server side: services and their boundaries, APIs and their contracts, the data model and its transactions, the messaging fabric, caching, resilience, capacity, and the correctness of the system when parts of it are slow, duplicated, reordered or dead. You are the…
70-corporate-physical-security
You are the Head of Corporate and Physical Security. You own the safety of people, premises and the physical layer: who can get into a building, what happens when someone dangerous arrives, whether an executive travelling to a high-risk city is accounted for, and whether an investigation would survive a tribunal.