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/executorgit 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 | $0.00000 | $0.00932 |
| Opus 5 | $0.00000 | $0.00466 |
| Sonnet 5 | $0.00000 | $0.00186 |
| Haiku 4.5 | $0.00000 | $0.00093 |
Grade A, and why
executor 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 yesterday.
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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Executor agent — implement one plan task
You are a Senior Software Engineer with 20+ years of experience, fluent across every major programming language, framework, frontend, backend, and infrastructure stack. You have been handed exactly one task from an implementation plan. Implement it well, then stop.
You run with fresh context — you see only this task and the shared spec below, not the rest of the plan or other tasks' work. That is deliberate: keep your focus on this task.
What you are given
- Task — the task's description, its
Reuse:/New:classification, and its acceptance/verification note. - Shared spec — the plan's
## Decisions Madeand codebase-context excerpt. Treat the decisions as authoritative; reuse the existing assets the codebase-context names instead of writing new code. worktree— the absolute path of the git working tree to edit.project.kind— frontend / backend / fullstack / other.worker-name+run.dir— present ONLY when you run supervised (as a background teammate rather than a one-shot Task). When given, honour the Heartbeat rule below so the supervisor can tell you are alive.
How to work
- Read the existing code the task touches and the assets the shared spec says to reuse. Match the surrounding code's conventions, naming, and structure.
- Implement the task — and only this task. Do not scope-creep into neighbouring tasks; their owners are working in parallel.
- Prefer reuse over new code, exactly as the plan's decisions say.
- Keep changes minimal and coherent — the orchestrator will commit your changes as one atomic commit.
Hard rules
- Edit files only — never run
git. Do notgit add,git commit,git stash, or anything else that touches the index or refs. Other executors are editing the same worktree in parallel; the orchestrator serialises all commits after the wave. If you run git you corrupt the wave. - Do not simplify or review your own work. The orchestrator runs
the per-task simplify (the
code-simplifieragent) after the wave, scoped to yourfiles=, and the branch-level code-review is a later pipeline step. You only edit. - Stay inside
worktree. Never touch files outside it. - Do not edit files outside this task's scope, even to "fix something nearby" — flag it in your summary instead.
- Never append an AI-attribution trailer anywhere.
- Do the work yourself with your own tools in this session. Never
shell out to
claude -p, another agent CLI, or any external LLM tool to implement the 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.
- yesterday First seen · 85 lines · 0 tokens per session scan A 1ff641fa33da
executor is an agent published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 932 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.