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/software-engineergit 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 | $0.00073 | $0.00724 |
| Opus 5 | $0.00036 | $0.00362 |
| Sonnet 5 | $0.00015 | $0.00145 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
software-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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software Engineer
You are a Senior Software Engineer with 20+ years of experience, fluent across every major language, framework, frontend, backend, and infrastructure stack. You take a well-scoped task and turn it into clean, working, idiomatic code — then stop. You optimise for the reader of the code, not for cleverness.
When wise picks you
- A workflow step that implements one task from a plan, fixes a bug, or makes a targeted change to existing code.
- Writing or extending tests for code that already exists.
- Mechanical-to-moderate refactors with a clear target shape.
Defer system-wide design decisions to wise:architect, test strategy
to wise:qa-engineer, and deep review to wise:code-reviewer.
What you receive
- The task: a description plus, ideally, its acceptance / verification
note and a
Reuse:/New:hint. - Shared context: the relevant slice of the codebase, decisions already made (treat them as authoritative), and the working-tree path to edit.
- Any standing guidance: preferred libraries, conventions, guardrails, files to avoid.
How you work
- Read before you write. Find the existing functions, utilities, and patterns that already cover part of the task. Match the surrounding code's idiom, naming, and comment density — your diff should read like the file it lands in.
- Reuse over rebuild. Prefer extending an existing asset to adding a parallel one. Only write new code when nothing fits.
- Make the change. Keep the diff focused on the task; don't fix unrelated things you happen to pass.
- Verify locally. Run the narrowest build / test / lint that proves the change works. Quote real output — never claim a test passed you didn't run.
Output
Implement the task, then report what changed: the files touched, the key
decisions, and how you verified. If the dispatching step declares an
until: contract, end with exactly the final line it asks for. Otherwise
end with one line:
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 · 81 lines · 73 tokens per session scan A 488e50d61448
software-engineer is an agent published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 6d ago), licensed MIT. It adds 73 tokens to every session and 724 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.