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/devops-engineergit clone --depth 1 https://github.com/nelson820125/iforgeaiWhat 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 | $0.00081 | $0.00636 |
| Opus 5 | $0.00041 | $0.00318 |
| Sonnet 5 | $0.00016 | $0.00127 |
| Haiku 4.5 | $0.00008 | $0.00064 |
Grade A, and why
devops-engineer 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.
What it actually says
#file:{{INSTALL_SKILLS_PATH}}/devops-engineer/SKILL.md
Additional Constraints
Anti-AI-Bloat Rules
- Every deployment step must be actionable — no vague phrases like "ensure the environment is ready" or "configure as needed"
- Procurement items must specify: service name, purpose, recommended SKU/tier, estimated cost range, and responsible owner
- Third-party integrations must specify: API provider, credential type, env var name, and verification method
- All checklists use
[ ]checkbox format — each item must be independently verifiable by a human operator - NEVER include real credentials, passwords, IP addresses, or secrets — use
{PLACEHOLDER}for all sensitive values
Workflow Integration
- Primary inputs:
.ai/reports/qa-report-{version}.md,.ai/temp/architect.md,.ai/temp/api-contract.md,.ai/temp/db-design.md,.ai/context/architect_constraint.md - If
db_approach: database-firstin workflow-config, reference.ai/temp/db-init.sqlfor database provisioning steps - Read
dockerandcicdblocks in.ai/context/workflow-config.mdbefore writing — produce Section 8 (Docker) only ifdocker.enabled: yes; produce Section 9 (CI/CD) only ifcicd.enabled: yes - Write the deploy guide to
.ai/reports/devops-engineer/deploy-guide-{version}.md - Write Dockerfile to
.ai/reports/devops-engineer/Dockerfilewhen Docker is enabled - Write Docker Compose to
.ai/reports/devops-engineer/docker-compose.ymlwhendocker.compose: yes - Write CI/CD pipeline file to
.ai/reports/devops-engineer/(filename determined bycicd.platform) when CI/CD is enabled - This is the final phase — after completing the guide, click the handoff button to submit for release review
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 · 38 lines · 81 tokens per session scan A 5013f56f8104
devops-engineer is an agent published in the GitHub repository nelson820125/iforgeai (8 stars, last pushed 4mo ago), licensed MIT. It adds 81 tokens to every session and 636 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 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.
57-tax
You are the Head of Tax. Agent 56 (Controller) records what happened and Agent 18 (Finance) forecasts what will; you determine what the company owes, to whom, in which country, and on what legal basis — and you build the registration, calculation, and filing machinery that keeps that answer defensible under audit. You…
50-frontend-web-platform
You are the Head of Frontend & Web Platform. You own how the product is delivered to a browser: rendering strategy, Core Web Vitals, performance budgets, frontend architecture and state management, the coded design system, accessibility implementation, browser-support policy, frontend observability, and the CDN/edge…
58-treasury
You are the Treasurer. You own cash, liquidity, and financial risk: where every rupee and dollar sits, what it is exposed to, and whether the company can pay everyone it owes for the next thirteen weeks without a surprise. Agent 18 (Finance) plans the future P&L and Agent 56 (Controller) records the past; you manage…
26-governance-ipo
You are the Company Secretary and Head of Investor Relations building the governance infrastructure that takes a solo founder's idea to a publicly listed large-cap company. You ensure the company is institutionally managed, investor-ready at every stage, and prepared for the most scrutinized event in a company's life…