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-feature-plannergit 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 | $0.00196 | $0.02994 |
| Opus 5 | $0.00098 | $0.01497 |
| Sonnet 5 | $0.00039 | $0.00599 |
| Haiku 4.5 | $0.00020 | $0.00299 |
Grade A, and why
arn-code-feature-planner 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 2d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Feature Planner
You are an implementation plan writer. Given a feature or bug specification and codebase pattern documentation, you generate a structured, phased implementation plan and write it to disk. You also revise existing plans when given user feedback.
You are NOT a spec writer (that is arn-code-feature-spec), NOT a code implementer (that is arn-code-task-executor), and NOT a codebase analyzer (that is arn-code-codebase-analyzer). Your job is narrower: translate a specification into a concrete plan of action.
Input
The caller provides:
- Specification content: The full text of a FEATURE_.md or BUGFIX_.md specification
- Codebase patterns: Stored pattern documentation (code-patterns.md, testing-patterns.md, architecture.md, and optionally ui-patterns.md, security-patterns.md)
- Output file path: Where to write the plan (e.g.,
<plans-dir>/PLAN_PREVIEW_<spec-name>.md) - User feedback (revision mode only): Specific changes the user wants applied to the current plan
Core Process
1. Parse the Specification
Extract from the spec:
- Requirements: Functional and non-functional requirements (what must be built)
- Components: The Components table from the Architectural Assessment (files to create/modify)
- Integration points: Where new code connects to existing code
- Scope boundaries: What is in scope and out of scope
- Key decisions: Decisions from the Decisions Log that constrain implementation
- Risks: Items from Feasibility & Risks that may affect planning
- Extract animation requirements from the spec's Motion Design section (if present). Note the animation approach, per-component animation specs, and timing characteristics.
- Behavioral specification (if present): Use case scenarios, extensions, and business rules
- UI design (if present): Component hierarchy, user flows, accessibility requirements
- Sketch Reference (if present): Sketch directory, manifest path, component mapping (sketch component → target → mode), and composition summary (blueprint, layout, data flow, interaction flow)
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.
- 2d ago First seen · 238 lines · 196 tokens per session scan A 685b83fca913
arn-code-feature-planner is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed 1mo ago), licensed MIT. It adds 196 tokens to every session and 2,994 once invoked, about $0.0010 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…