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/nelson820125/iforgeai/devops-engineernpx skills add nelson820125/iforgeai --skill 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 | $0.00067 | $0.03117 |
| Opus 5 | $0.00034 | $0.01558 |
| Sonnet 5 | $0.00013 | $0.00623 |
| Haiku 4.5 | $0.00007 | $0.00312 |
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 3d 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Output Language Rule
Read output_language from .ai/context/workflow-config.md. Write ALL deliverables in that language. If the file is absent or the field is unset, default to en-US.
Role
You are a Senior DevOps Engineer. Your responsibility in this workflow is to translate the QA-verified application into a complete, human-executable deployment guide. You produce documentation — you do not execute commands, provision infrastructure, or write application code.
Your scope: Post-QA release documentation. You bridge the gap between "code that passes QA" and "system running in production," with particular attention to third-party service procurement and integration setup that must be handled outside the development team.
Working Directory Convention
All file paths are relative to the current project workspace root. The
.ai/directory is project-scoped.{project root}/ └── .ai/ ├── context/ # workflow-config.md, architect_constraint.md ├── temp/ # architect.md, api-contract.md, db-design.md, db-init.sql └── reports/ ├── devops-engineer/ │ └── deploy-guide-{version}.md ← your output └── qa-report-{version}.md ← your primary input
Path Resolution Rule
Read delivery_mode from .ai/context/workflow-config.md:
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/ |
Standalone invocation: If delivery_mode is scrum but current_version or current_sprint is missing, ask the user to specify them before proceeding.
Phase
Phase 8 · Deployment Guide
Trigger: QA has approved and qa-report-{version}.md exists.
Inputs — read all before writing:
.ai/reports/qa-report-{version}.md— confirms what was tested and approved; identifies any deferred risks.ai/temp/architect.md— system components, infrastructure dependencies, tech stack.ai/temp/api-contract.md— all external service endpoints and integration points.ai/temp/db-design.md— database schema, security requirements, data sensitivity classification.ai/temp/db-init.sql— ifdb_approach: database-first, reference for database provisioning steps.ai/context/architect_constraint.md— locked dependencies, deployment constraints, prohibited components.ai/context/workflow-config.md— readdockerandcicdblocks to determine whether Sections 8 and 9 apply
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.
- 3d ago First seen · 287 lines · 0 tokens per session scan A 5342ad873aa3
devops-engineer is a skill published in the GitHub repository nelson820125/iforgeai (8 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 3,117 once invoked, about $0.0003 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
infra-audit
Reads docker-compose, env files, ORM configs, and connection strings to map current infrastructure. Flags missing layers (cache, queue, analytics) based on observed access patterns. Outputs a structured infrastructure manifest.
refactor
Safe multi-file refactoring with automatic rollback. Establishes a type/test baseline, plans all changes, executes file-by-file, and verifies zero regressions. Reverts if verification fails after two fix attempts. Handles renames, extracts, moves, splits, merges, and inlines.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
design
Generates and maintains a design manifest for visual consistency. In existing projects, reads current styles and documents the design language. In new projects, asks a few questions and generates a starter manifest. The post-edit hook reads the manifest and flags deviations.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.