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 skills/appsvortex/arness/arn-code-assessnpx skills add AppsVortex/arness --skill arn-code-assessgit 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 | $0.00133 | $0.03867 |
| Opus 5 | $0.00067 | $0.01934 |
| Sonnet 5 | $0.00027 | $0.00773 |
| Haiku 4.5 | $0.00013 | $0.00387 |
Grade A, and why
arn-code-assess 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 — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Assess
Run a comprehensive technical assessment of the codebase against stored patterns, let the user prioritize findings, then orchestrate the full Arness pipeline (spec → plan → execute → test → ship) for multiple improvements in a single session.
This skill is a sequencer and decision-gate handler, like arn-planning. It MUST NOT duplicate sub-skill or agent logic. All pipeline work is done by the invoked skills and agents. This skill handles: scope selection, assessment orchestration, finding prioritization, multi-spec pipeline management, and progress display.
Prerequisites
Check for a ## Arness section in the project's CLAUDE.md. If missing, inform the user: "Arness is not configured for this project yet. Run /arn-assessing to get started — it will set everything up automatically." Do not proceed without it.
Additionally, verify that pattern files exist at the configured code-patterns path. At minimum, these must exist:
code-patterns.mdtesting-patterns.mdarchitecture.md
If any required pattern file is missing, inform the user: "Pattern documentation is incomplete. Run /arn-assessing which will generate pattern docs on first use."
Decision Gates
The skill pauses at exactly 7 gates. Steps marked (auto) flow without stopping.
| Gate | When | Question | Options |
|---|---|---|---|
| G1 | Entry | "What would you like to assess?" | Entire codebase / Specific area |
| G2 | After assessment | "Ready to prioritize?" | Prioritize / Investigate further |
| G3 | After prioritization | "How should improvements be organized?" | Bundle all / Separate specs / Arness suggests groupings |
| G4 | After all plans generated | "Plans ready. Proceed?" | Approve all / Revise specific plan / Remove a spec |
| G5 | Before each subsequent spec execution | "Conflict detected" (conditional) | Re-plan / Proceed / Skip |
| G6 | After test results | "Tests [pass/fail]. Proceed?" | Ship / Fix and re-test / Abort |
| G7 | Final | "Ship it?" | Commit, push & PR / Just commit / Not yet |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 391 lines · 133 tokens per session scan A 7e1bb4e7c83f
arn-code-assess is a skill published in the GitHub repository AppsVortex/arness (33 stars, last pushed 1mo ago), licensed MIT. It adds 133 tokens to every session and 3,867 once invoked, about $0.0007 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 skills, from other repositories
agent-framework-azure-ai-py
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
agentmail
Email infrastructure for AI agents. Create accounts, send/receive emails, manage webhooks, and check karma balance via the AgentMail API.
aria
Designs the data model, API contracts, and structural foundation of the system.
luna
Reviews code for objective correctness, security, and reliability.
max
Cleans up and improves existing code without changing behavior.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.