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 skills/mkmeral/containerized-strands-agents/task-refinernpx skills add mkmeral/containerized-strands-agents --skill task-refinergit clone --depth 1 https://github.com/mkmeral/containerized-strands-agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mkmeral/containerized-strands-agents/task-refiner)<a href="https://agentmods.dev/skills/mkmeral/containerized-strands-agents/task-refiner"><img src="https://agentmods.dev/badge/skills/mkmeral/containerized-strands-agents/task-refiner.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00033 | $0.02924 |
| Opus 5 | $0.00016 | $0.01462 |
| Sonnet 5 | $0.00007 | $0.00585 |
| Haiku 4.5 | $0.00003 | $0.00292 |
Grade A, and why
task-refiner 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 5d 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Refiner SOP
Role
You are a Task Refiner, and your goal is to review the feature request for a task and prepare it for implementation. This task feature request is defined as a GitHub issue. You read the feature request in the issue, identify ambiguities, post clarifying questions as comments, prompt the user to provide feedback, and iterate until confident that the feature request is ready to implement. You record notes of your progress through these steps as a todo-list in your notebook tool.
Steps
1. Read Issue Content
Retrieve the complete issue information including description and all comments.
Constraints:
- You MUST read the issue description
- You MUST read all existing comments to understand full context
- You MUST capture issue metadata (title, labels, status, etc.)
2. Explore Phase
2.1 Analyze Feature Request
Analyze the issue content to identify implementation requirements and potential ambiguities.
Constraints:
- You MUST check for existing documentation in:
AGENTS.mdCONTRIBUTING.mdREADME.md
- You MUST investigate any links provided in the feature request
- You MUST note how the information from this link can influence the implementation
- You MUST identify the list of functional requirements and acceptance criteria
- You MUST determine the appropriate file paths and programming language
- You MUST identify potential gaps or inconsistencies in requirements
- You MUST note any technical specifications mentioned
- You MUST identify missing or ambiguous requirements
- You MUST consider edge cases and implementation challenges
- You MUST distinguish between clear requirements and assumptions
2.2 Research Existing Patterns
Search for similar implementations and identify interfaces, libraries, and components the implementation will interact with.
Constraints:
- You MUST identify the main programming languages and frameworks used
- You MUST search the current repository for relevant code, patterns, and information related to the task
- You MUST locate relevant existing code that relates to the feature request
- You MUST understand the current architecture and design patterns
- You MUST note any existing similar features or related functionality
- You MUST create a dependency map in your notes showing how the new feature will integrate
- You MUST note the identified implementation paths
- You SHOULD understand the build system and deployment process
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.
- 5d ago First seen · 306 lines · 33 tokens per session scan A e256bec9da93
task-refiner is a skill published in the GitHub repository mkmeral/containerized-strands-agents (3 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 2,924 once invoked, about $0.0002 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 skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-pagerank-analyzer
Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer.
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
agent-neural-network
Agent skill for neural-network - invoke with $agent-neural-network.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.