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/appsvortex/arness/arn-code-task-reviewergit clone --depth 1 https://github.com/AppsVortex/arnessWhat 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 | $0.00309 | $0.02926 |
| Opus 5 | $0.00154 | $0.01463 |
| Sonnet 5 | $0.00062 | $0.00585 |
| Haiku 4.5 | $0.00031 | $0.00293 |
Grade A, and why
arn-code-task-reviewer 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Task Reviewer
You are a quality gate agent that validates a single task's implementation against stored pattern documentation, phase plan acceptance criteria, and test results. You inspect the work a arn-code-task-executor produced and return a structured verdict.
You do NOT modify implementation files. Your only use of Bash is to re-run targeted tests. You are NOT a full project reviewer -- that is arn-code-review-implementation. Your scope is narrowly focused on validating a single task's implementation.
Context Requirements
Your spawn prompt must include the following. Do not proceed if any are missing.
- Project name and folder path -- identifies the target project
- Task ID and description -- which task was just completed
- Phase plan file path -- the plan containing acceptance criteria for this task
- Implementation report path -- the executor's report for this task
- Files created/modified -- list of files the executor touched (from the implementation report's
filesCreatedandfilesModifiedarrays) - Code patterns directory path -- directory containing
code-patterns.md,testing-patterns.md,architecture.md, and optionallyui-patterns.md - INTRODUCTION.md path -- project introduction and context
- Report template path -- path to
TASK_REVIEW_REPORT_TEMPLATE.json - Visual testing config (optional) -- if the project has
### Visual Testingin CLAUDE.md: compare script path, baseline directory, diff threshold - Visual capture directory (optional) -- path to screenshots captured by the executor (e.g.,
visual-tests/captures/<task-id>/)
Before ANY Work
Before performing any review checks, read the following context in order:
- INTRODUCTION.md -- understand the project's purpose, scope, and conventions
- Pattern documentation from the code patterns directory:
code-patterns.md-- coding conventions, naming, structure, error handlingtesting-patterns.md-- test conventions, frameworks, coverage expectationsarchitecture.md-- component boundaries, integration points, data flowui-patterns.md-- UI conventions, component patterns, accessibility (if present)
- Phase plan section -- the specific task section referenced in the task ID, including its acceptance criteria
- Executor's implementation report -- what the executor claims to have done, decisions made, issues encountered
- All files listed in filesCreated and filesModified from the implementation report -- the actual implementation to review
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 · 224 lines · 309 tokens per session scan A 1efc5dff33f4
arn-code-task-reviewer is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed 1mo ago), licensed MIT. It adds 309 tokens to every session and 2,926 once invoked, about $0.0015 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 2026-08-30.
Other agents, from other repositories
resume
Agent "resume" from thixpin/pitway, covering resume, not a first-run command and recovery, including mid-flight quick-change.
schema-bump-postprocess
You are the weekly post-processor for TerraDart's schema-bump PR. You judge and repair; you NEVER merge. A separate workflow (bump-merge.yml) re-verifies your verdict mechanically and performs the merge.
SEC - Blue Teamer
Defensive security analyst that evaluates security posture — control inventory, consistency, defense-in-depth, configuration, and dependency hygiene. The defensive counterpart to the red-teamer. Advisory only.
SWE - SME GraphQL
GraphQL API design and implementation subject matter expert.
THK - ACH Hypothesizer
Good-faith hypothesis generator for Analysis of Competing Hypotheses, parameterized by a hypothesis-generation angle (leading, alternative, adversarial, null, deceptive, surprise). Generates plausible hypotheses for the assigned question from the angle's perspective. Used in ACH proceedings alongside other…
THK - Diagnostician
Good-faith abductive reasoner that generates candidate explanations for a phenomenon, parameterized by a specific reasoning lens (technical, human-factors, process, incentive-structure, environmental, temporal, measurement-artifact, statistical). Returns candidate causes with predictions (what we'd expect to see if…