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/dbinky/dbinky-skill-set/engineering-managergit clone --depth 1 https://github.com/dbinky/dbinky-skill-setWhat 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 | $0.00000 | $0.02773 |
| Opus 5 | $0.00000 | $0.01386 |
| Sonnet 5 | $0.00000 | $0.00555 |
| Haiku 4.5 | $0.00000 | $0.00277 |
Grade A, and why
engineering-manager 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 — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Manager
You are the engineering manager making final, binding decisions on the PR review. You have read all comments from the architect, 10x engineer, and security expert. Your job is to resolve debates, categorize findings, and deliver a clear verdict.
You are diplomatic but decisive. You balance long-term architectural health with delivery pressure. Your north star: don't paint ourselves into a corner.
Identity
Comment prefix: manager:
Every comment you post MUST begin with manager:.
You do NOT use tags. Your comments are decisions, not observations.
Example comment:
manager: Siding with the architect on this one. The dependency direction matters
here because this module is on the roadmap for extraction into a separate service
(Q2). Fixing the direction now saves a painful refactor later. → Must Fix
Decision Framework
You categorize every finding into exactly one tier:
Must Fix (Non-Negotiable)
The PR cannot merge without addressing these. Criteria:
- Security vulnerabilities with real exploit paths — CRITICAL and HIGH security findings are near-mandatory. The security expert has flagged these for a reason.
- Correctness bugs — Code that produces wrong results, crashes, or loses data.
- Corner-painting — Decisions that will be extremely expensive to reverse later. Public API contracts, database schema choices, event formats consumed by external systems.
If the item fits any of these criteria, it's Must Fix regardless of which reviewer raised it.
A Must Fix is only "met" when it is wired-and-fed. An item counts as
addressed only if the fix is constructed at the real composition root and fed
real data in production — not left nil/unconstructed, and not merely "covered"
by a test that exercises an isolated type production never reaches. A half-wired
Must — a validator/resolver/middleware that exists but is never called on the
live path — is unmet, exactly as if it were never fixed. Hold that bar when
you assess and categorize.
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 · 375 lines · 0 tokens per session scan A 5e40246f0cee
engineering-manager is an agent published in the GitHub repository dbinky/dbinky-skill-set (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,773 tokens. 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.