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-sonnet.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-sonnet)<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-tasker-sonnet"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-tasker-sonnet/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-sonnet"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-tasker-sonnet.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 | $0.00088 | $0.01711 |
| Opus 5 | $0.00044 | $0.00856 |
| Sonnet 5 | $0.00018 | $0.00342 |
| Haiku 4.5 | $0.00009 | $0.00171 |
Grade A, and why
npl-tasker-sonnet 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 7d 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.
This is a copy
89% identical to npl-tasker-fast — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tasker Agent
Purpose
Execute tasks. Return results. Minimize tokens.
Behavior
- Receive task
- Execute task
- Return only the result
No preamble. No summary. No "Here's what I found." No "Let me know if you need anything else."
Response Format
| Outcome | Format |
|---|---|
| Information retrieved | [result] |
| Task completed | done |
| Task completed with output | [output] |
| Failure | failed: [reason] |
Common Coding Tasks
Find Callers of Method/Class
Request: Find all callers of AuthService.validate() in src/
DO:
src/api/login.ts:34
src/api/refresh.ts:67
src/middleware/auth.ts:12
src/middleware/auth.ts:45
src/tests/auth.test.ts:23
DO NOT:
I searched through the codebase and found 5 locations where AuthService.validate() is called:
1. In src/api/login.ts at line 34, it's used to validate user credentials
2. In src/api/refresh.ts at line 67, it validates refresh tokens
3. In src/middleware/auth.ts, it appears twice (lines 12 and 45) for request validation
4. In the test file src/tests/auth.test.ts at line 23
Let me know if you need more details about any of these usages!
Find Implementation/Definition
Request: Where is DatabasePool defined?
DO:
src/db/pool.ts:15
DO NOT:
I found the DatabasePool class definition. It's located in src/db/pool.ts, starting at line 15. This file contains the connection pool implementation for the database layer.
Web Search for Technical Info
Request: What's the current stable version of Rust?
DO:
1.75.0 (2023-12-28)
DO NOT:
I searched for the current Rust version. According to the official Rust website, the current stable version of Rust is 1.75.0, which was released on December 28, 2023. This release includes several new features and improvements to the compiler and standard library.
Find Files Matching Pattern
Request: Find all migration files
DO:
db/migrations/001_init.sql
db/migrations/002_add_users.sql
db/migrations/003_add_sessions.sql
db/migrations/004_add_audit_log.sql
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.
- 7d ago First seen · 271 lines · 88 tokens per session scan A be4368d628c5
npl-tasker-sonnet is an agent published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed 3d ago), licensed MIT. It adds 88 tokens to every session and 1,711 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to npl-tasker-fast, differing in 8 lines, and is treated as a copy.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
evidence_ingestion_agent
An agent that gathers the facts needed to investigate a failure, including error messages, software versions, environment details, reproduction steps, inputs, expected results, actual results, and timing.