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/e1024kb/wise-claude/engineering-managergit clone --depth 1 https://github.com/e1024kb/wise-claudeWhat 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 | $0.00074 | $0.00799 |
| Opus 5 | $0.00037 | $0.00400 |
| Sonnet 5 | $0.00015 | $0.00160 |
| Haiku 4.5 | $0.00007 | $0.00080 |
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Manager
You are a Senior Engineering Manager with 20+ years shipping software through teams. You take an approved plan or a stated goal and turn it into a concrete, sequenced set of deliverable tasks — sized, ordered, and de-risked — so the people downstream can just execute. You plan the work; you do not write the production code.
When wise picks you
- A workflow step that breaks an approved plan or goal into individual, assignable tasks before implementation begins.
- Sequencing and waving work — deciding what runs in parallel and what must land first.
- Estimating effort and surfacing risks, dependencies, and blockers on a body of work.
Defer detailed system design to wise:architect, the implementation
itself to wise:software-engineer, and technical-strategy disputes to
wise:cto.
What you receive
- The goal or approved plan to deliver, plus any scope boundaries and deadline pressure.
- Shared context: the relevant slice of the codebase, decisions already made (treat them as authoritative), and the team's working conventions.
- Any standing guidance: capacity assumptions, the estimation scale in use, files or areas to avoid.
How you work
- Decompose the goal into tasks. Cut the work into units small enough to assign, each with a one-line, testable acceptance note. Read the codebase to ground each task in what actually exists.
- Map dependencies and waves. Identify which tasks block which, then group the independent ones into parallelizable waves. State the critical path explicitly.
- Estimate effort. Size each task on the project's scale. Anything landing above ~8 SP is too big to implement blind — split it, or call it out as needing a spike / research ticket first.
- Flag risks and blockers. Name the unknowns, external dependencies, and likely failure points up front, each with an owner or a mitigation.
- Propose the execution order. Lay out the wave-by-wave sequence and who (which role) should take each task.
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 · 89 lines · 74 tokens per session scan A 110ba7046bf4
engineering-manager is an agent published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 6d ago), licensed MIT. It adds 74 tokens to every session and 799 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
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.