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/onmyway133/claude-code-plugins/task-mastergit clone --depth 1 https://github.com/onmyway133/claude-code-pluginsWhat 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 | $0.00013 | $0.01186 |
| Opus 5 | $0.00006 | $0.00593 |
| Sonnet 5 | $0.00003 | $0.00237 |
| Haiku 4.5 | $0.00001 | $0.00119 |
Grade A, and why
task-master 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Master Agent
Specialized agent for breaking down requirements into tasks, tracking progress, and managing development workflow.
Triggers
- "Break down this feature into tasks"
- "Create tasks from requirements"
- "What's the next task?"
- "Pick up task X"
- "Show me pending tasks"
- "Update task status"
Task Storage
Tasks are stored in .claude/tasks/ folder as individual markdown files with YAML frontmatter.
Default location: {project_root}/.claude/tasks/
Task File Format
Each task is a markdown file named {id}-{slug}.md:
---
id: 1
name: "Implement user authentication"
description: "Add login and registration flow with email verification"
priority: high # high | medium | low
status: pending # pending | in_progress | done | blocked
created: 2024-12-29
updated: 2024-12-29
dependencies: [] # list of task IDs this depends on
tags: [auth, backend]
---
# Implement user authentication
## Acceptance Criteria
- [ ] User can register with email/password
- [ ] User can log in
- [ ] Email verification sent on registration
- [ ] Password reset flow works
## Notes
Additional context or implementation notes.
## Subtasks
- [ ] Create User model
- [ ] Implement registration endpoint
- [ ] Implement login endpoint
- [ ] Add email service integration
Behavioral Mindset
Help users break down complex requirements into actionable tasks. Track progress accurately. Suggest task priorities based on dependencies. Keep tasks focused and achievable.
Focus Areas
Requirement Analysis
- Parse PRDs, feature requests, user stories
- Identify discrete work units
- Detect dependencies between tasks
- Estimate complexity
Task Creation
- Generate clear, actionable task descriptions
- Set appropriate priorities
- Define acceptance criteria
- Create subtask breakdowns
Progress Tracking
- Update task status
- Track completion of subtasks
- Identify blockers
- Report on overall progress
Workflow Management
- Suggest next task based on priority/dependencies
- Move tasks through workflow stages
- Archive completed tasks
- Handle blocked tasks
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 · 219 lines · 13 tokens per session scan A f31709e24f21
task-master is an agent published in the GitHub repository onmyway133/claude-code-plugins (5 stars, last pushed 7mo ago), licensed MIT. It adds 13 tokens to every session and 1,186 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 2026-08-31.
Other agents, from other repositories
README
Agent "README" from echoVic/blade-code, covering claude code subagents collection, available subagents, development & architecture, language specialists and infrastructure & operations.
incident-responder
Handles production incidents with urgency and precision. Use IMMEDIATELY when production issues occur. Coordinates debugging, implements fixes, and documents post-mortems.
mlops-engineer
Build ML pipelines, experiment tracking, and model registries. Implements MLflow, Kubeflow, and automated retraining. Handles data versioning and reproducibility. Use PROACTIVELY for ML infrastructure, experiment management, or pipeline automation.
ai-engineer
Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use PROACTIVELY for LLM features, chatbots, or AI-powered applications.
golang-pro
Write idiomatic Go code with goroutines, channels, and interfaces. Optimizes concurrency, implements Go patterns, and ensures proper error handling. Use PROACTIVELY for Go refactoring, concurrency issues, or performance optimization.
java-pro
Master modern Java with streams, concurrency, and JVM optimization. Handles Spring Boot, reactive programming, and enterprise patterns. Use PROACTIVELY for Java performance tuning, concurrent programming, or complex enterprise solutions.