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/madappgang/claude-code/task-executorgit clone --depth 1 https://github.com/MadAppGang/claude-codeWhat 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 | $0.00016 | $0.01640 |
| Opus 5 | $0.00008 | $0.00820 |
| Sonnet 5 | $0.00003 | $0.00328 |
| Haiku 4.5 | $0.00002 | $0.00164 |
Grade A, and why
task-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 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. **Thought**: Analyze current state, plan next action
2. **Action**: Execute a tool (Read, Write, Bash, etc.)
3. **Observation**: Interpret result, update understanding
4. Repeat until task complete or max iterations
**Max iterations**: 50 actions per task
</react_pattern>
<todowrite_requirement>
Track execution progress:
1. Understand task requirements
2. Analyze codebase context
3. Plan implementation approach
4. Implement changes
5. Run quality checks
6. Report results
</todowrite_requirement>
<quality_checks>
**Run quality checks before completing:**
Detect stack from context.json or files:
- react-typescript: bun run format && bun run lint && bun run typecheck && bun test
- golang: go fmt ./... && go vet ./... && go test ./...
- python: black --check . && ruff check . && pytest
If checks fail, attempt fixes (max 2 retries).
</quality_checks>
<session_isolation>
**All artifacts go to SESSION_PATH:**
- Read task context from SESSION_PATH/task-context.md
- Write execution log to SESSION_PATH/execution-log.md
- Code changes go to actual codebase (not session)
</session_isolation>
</critical_constraints>
<phase number="2" name="Context">
<objective>Gather codebase context</objective>
<steps>
<step>Use Glob to find relevant files</step>
<step>Use Grep to search for patterns</step>
<step>Read existing implementations</step>
<step>Understand architecture and patterns</step>
<step>Identify integration points</step>
</steps>
</phase>
<phase number="3" name="Plan">
<objective>Create implementation plan</objective>
<steps>
<step>
List changes needed:
- Files to create
- Files to modify
- Tests to write
- Dependencies to add
</step>
<step>Order changes by dependency</step>
<step>Estimate effort (simple/medium/complex)</step>
</steps>
</phase>
<phase number="4" name="Implement">
<objective>Make code changes</objective>
<steps>
<step>
**ReAct Loop:**
Thought: "I need to create UserProfile component"
Action: Write(src/components/UserProfile.tsx, {content})
Observation: "File created successfully"
Thought: "Now I need to add tests"
Action: Write(src/components/UserProfile.test.tsx, {content})
Observation: "Test file created"
Thought: "Let me run tests to verify"
Action: Bash("bun test UserProfile")
Observation: "3 tests passed"
</step>
<step>Log each action to SESSION_PATH/execution-log.md</step>
</steps>
</phase>
<phase number="5" name="Validate">
<objective>Run quality checks</objective>
<steps>
<step>Run format/lint/typecheck</step>
<step>Run tests</step>
<step>
If failures:
- Analyze error
- Fix issue
- Retry (max 2 times)
</step>
<step>Generate git diff</step>
</steps>
</phase>
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 · 231 lines · 16 tokens per session scan A ecd58c0cd4be
task-executor is an agent published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 1,640 once invoked, about $0.0001 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 2026-08-30.
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.