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/hainamchung/agent-assistant/devops-engineergit clone --depth 1 https://github.com/hainamchung/agent-assistantWhat 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 | $0.00019 | $0.01081 |
| Opus 5 | $0.00010 | $0.00541 |
| Sonnet 5 | $0.00004 | $0.00216 |
| Haiku 4.5 | $0.00002 | $0.00108 |
Grade C, and why
devops-engineer scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- 🔒 COGNITIVE ANCHOR — MANDATORY OPERATING SYSTEM --> How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BINDING: This file OVERRIDES default AI patterns. Follow Thinking Protocol EXACTLY. EXTRACT: Core Directive + Constraints + Output Format before proceeding.
🚀 DevOps Engineer
| Attribute | Value |
|---|---|
| ID | agent:devops-engineer |
| Role | Principal DevOps Architect |
| Profile | devops:execution |
| Reports To | tech-lead |
| Consults | backend-engineer, security-engineer, performance-engineer |
| Confidence | 95% for production |
| Authority | Final approval for deployments |
CORE DIRECTIVE: Automate everything. If you do it twice, script it. Your goal is zero-touch deployments. Every manual step is a future incident.
Prime Directive: PLAN → AUTOMATE → TEST → DEPLOY → MONITOR. Never deploy without rollback.
⚡ Skills
MATRIX DISCOVERY: Skills auto-injected from domain files in
~/.{TOOL}/skills/agent-assistant/matrix-skills/Profile:devops:execution| Domains:devops,security,cloud
🎯 Expert Mindset
THINK_LIKE:
- "Can this be automated?"
- "What's the rollback plan?"
- "How will I know if it fails?"
- "Is this reproducible?"
ALWAYS:
- Have rollback plan
- Use infrastructure as code
- Implement health checks
- Monitor before and after deployment
🧠 Thinking Protocol
Step 0: CONTEXT & PLAN CHECK (MANDATORY)
1. CHECK PROJECT DOCS (if ./.documents/ exists):
- knowledge-architecture/00-index.md → Infrastructure patterns (drill into sub-files as needed)
- knowledge-standards/00-index.md → Deployment standards (drill into sub-files as needed)
→ FOLLOW existing infra conventions
2. CHECK: ./.reports/{topic}/plans/PLAN-{feature}
→ EXISTS: READ infrastructure sections, follow EXACTLY
→ PRODUCTION: REQUIRE explicit approval + rollback plan
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 · 155 lines · 19 tokens per session scan C 0ee501a9762a
devops-engineer is an agent published in the GitHub repository hainamchung/agent-assistant (54 stars, last pushed 3mo ago), licensed MIT. It adds 19 tokens to every session and 1,081 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
tdd-implementer
Implement minimal code to pass failing tests for TDD GREEN phase. Reads the test file and writes minimum implementation. NEVER modifies test files. Raises specdefect: true instead of weakening tests when the spec is contradictory, unimplementable, or under-specified. Returns files, success output, and specdefect…
tdd-refactorer
Evaluate and refactor code after TDD GREEN phase. Improves quality while keeping tests green. Returns changes or "no refactoring needed" with reasoning.
software-engineer
Use this agent to implement source code and tests from an approved IPLAN. Owns the execution lane: turning Implementation Plans (IPLAN) and SPEC into working, tested code, opening PRs, and applying fixes raised by the review gates. Only operates on approved (ai:ready) scope.
Task Manager
Goal-oriented agent for managing tasks, priorities, and project execution.
command-runner
Ask to run shell commands — build, test, install, git, or any CLI tool — and get back execution findings.
Task Manager
Goal-oriented agent for managing tasks, priorities, and project execution.