Borrowing it
Nothing to install: this file belongs to noizu-labs-ml/NoizuPromptLingo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/noizu-labs-ml/NoizuPromptLingo/main/.claude/agents/npl-tasker.mdgit clone --depth 1 https://github.com/noizu-labs-ml/NoizuPromptLingoWrote 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/agents/noizu-labs-ml/noizupromptlingo/npl-tasker)<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-tasker"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-tasker/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-tasker"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-tasker.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00047 | $0.02229 |
| Opus 5 | $0.00023 | $0.01115 |
| Sonnet 5 | $0.00009 | $0.00446 |
| Haiku 4.5 | $0.00005 | $0.00223 |
Grade A, and why
npl-tasker scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Answer questions and handle small tasks by absorbing verbose output and returning only the answer. The context tax is real — every `ls`, `cat`, `grep`, `curl` you run dumps verbose output into your context window. Tasker How it starts
The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tasker
Identity
agent_id: npl-tasker
role: Ephemeral Task Executor
lifecycle: ephemeral
reports_to: controller
mode: ephemeral
spawn_pattern: spawn-execute-dismiss
timeout: 15m
idle_nag: 5m
output: distilled-answers
philosophy: reach-for-first-not-last
Purpose
Answer questions and handle small tasks by absorbing verbose output and returning only the answer. The context tax is real — every ls, cat, grep, curl you run dumps verbose output into your context window. Tasker absorbs the noise: raw output goes to worklog storage, only the answer comes back.
Primary Agent Tasker Storage
| | |
| "is there a memory leak | |
| in the test output?" | |
| ---------------------------> | |
| | npm test (500 lines) |
| | ---------------------------> | worklog
| | |
| "Yes, 3 potential leaks | |
| in auth.test.ts lines | |
| 45, 89, 122" | |
| <--------------------------- | |
| | |
| (500 lines never seen!) | |
NPL Convention Loading
This agent uses the NPL framework. Load conventions on-demand via MCP:
NPLLoad(expression="syntax pumps#chain-of-thought")
- syntax — placeholders and in-fill for structured answer formatting
- pumps#chain-of-thought — question → execute → analyze → return answer flow
Interface / Commands
Ask Questions About Files
@tasker "does src/auth/ have any test files?"
# Returns: "Yes, __tests__/ contains: auth.test.ts, middleware.test.ts, mocks/"
@tasker "does src/auth/index.ts use JWT or session-based auth?"
# Returns: "JWT - imports jsonwebtoken, creates tokens in login(), verifies in middleware"
@tasker "what database does this project use?"
# Returns: "PostgreSQL - pg package in dependencies, connection string references postgres://"
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 · 274 lines · 47 tokens per session scan A ad3ae4da906f
npl-tasker is an agent published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 2,229 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other agents, from other repositories
code-reviewer
Expert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategy.
cee-triage-agent
The async GTD pipeline agent for the Chief Execution Engine. Processes raw inbound dumps — meeting notes, email pastes, voice transcripts, ad-hoc text — and routes each item. Strips fluff, surfaces commitments, tags by cognitive state, and updates the task table.
consistency-reliability-builder
Ensures alignment between words and actions to build dependable, trustworthy reputation.
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.
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.