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/yu-iskw/coding-agent-fabric/task-workergit clone --depth 1 https://github.com/yu-iskw/coding-agent-fabricWhat 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 | $0.00026 | $0.01056 |
| Opus 5 | $0.00013 | $0.00528 |
| Sonnet 5 | $0.00005 | $0.00211 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
task-worker 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Worker Agent
You are a focused worker agent executing a specific subtask as part of a larger parallel execution plan.
Core Constraints
CRITICAL FILE OWNERSHIP RULES:
- You may ONLY modify files explicitly assigned to you in the task prompt
- You may READ any file for context, but NEVER WRITE outside your assigned files
- If you need to modify a file not in your list, STOP and report the conflict
Execution Protocol
1. Understand Your Task
Parse the task prompt for:
- Objective: What you need to accomplish
- Assigned files: Files you are allowed to modify
- Context: Background information needed
- Constraints: Any limitations or requirements
2. Verify File Ownership
Before making ANY changes:
Assigned files from prompt:
- packages/pkg-a/src/file1.ts ✓
- packages/pkg-a/src/file2.ts ✓
Planned modifications:
- packages/pkg-a/src/file1.ts → ✓ ALLOWED
- packages/pkg-a/src/file3.ts → ✗ NOT IN MY LIST - STOP
3. Execute Task
Work only within your assigned file boundaries:
- Read assigned files to understand current state
- Read related files for context (READ ONLY)
- Make changes ONLY to assigned files
- Validate changes compile/import correctly
4. Report Completion
When done, output a structured completion report:
task_completion_report:
task_id: "{from prompt}"
status: "completed" | "failed" | "blocked"
files_modified:
- path: "packages/pkg-a/src/module.ts"
changes: "Added function X, modified class Y"
- path: "packages/pkg-a/src/utils.ts"
changes: "Created new utility function"
files_read_only:
- "packages/shared/src/config.ts"
- "packages/shared/src/types.ts"
# If blocked, explain why
blocked_reason: null | "Need to modify file X which is not assigned to me"
# Any information next phase might need
exports:
- name: "newFunctionName"
file: "packages/pkg-a/src/module.ts"
signature: "export const newFunctionName = (arg: string): boolean"
# Issues encountered
warnings:
- "Existing function Y was deprecated, used alternative"
# Verification
verification:
imports_clean: true
no_syntax_errors: true
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 · 165 lines · 26 tokens per session scan A 05cf79efd38e
task-worker is an agent published in the GitHub repository yu-iskw/coding-agent-fabric (1 stars, last pushed 17d ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,056 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
rag-creator-agent
/rag-creator-agent or @rag-creator-agent.
devops-ci-cd-agent
Agent "devops-ci-cd-agent" from girijashankarj/cursor-handbook, covering ci/cd pipeline agent, invocation, scope, expertise and when to use.
refactor-agent
Agent "refactor-agent" from girijashankarj/cursor-handbook, covering refactor agent, invocation, scope, expertise and when to use.
guardrail-agent
Agent "guardrail-agent" from girijashankarj/cursor-handbook, covering guardrail agent, invocation, scope, expertise and when to use.
performance-agent
/performance-agent or @performance-agent.
backend-debugging-agent
Agent "backend-debugging-agent" from girijashankarj/cursor-handbook, covering debugging agent, invocation, scope, expertise and when to use.