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-catch-upnpx skills add AppsVortex/arness --skill arn-code-catch-upgit 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 | $0.00087 | $0.02656 |
| Opus 5 | $0.00044 | $0.01328 |
| Sonnet 5 | $0.00017 | $0.00531 |
| Haiku 4.5 | $0.00009 | $0.00266 |
Grade A, and why
arn-code-catch-up 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Catch-Up
Developers sometimes bypass the pipeline for quick fixes -- the "2am gap." These commits ship without specs, plans, or records, leaving holes in the artifact trail. Catch-up scans git history, identifies commits that have no corresponding Arness artifacts, and generates lightweight CATCHUP_ records in the CHANGE_RECORD.json envelope. The records are honest about what can and cannot be recovered retroactively: they document what changed (files, diffs, commit messages) and explicitly flag what is unknown (intent, test coverage, architectural reasoning).
This is a standalone skill. It operates outside the main pipeline and can be run at any time.
Step 0: Ensure Configuration
Read ${CLAUDE_PLUGIN_ROOT}/skills/arn-code-ensure-config/references/step-0-fast-path.md and follow its instructions. This guarantees a user profile exists and ## Arness is configured with Arness Code fields before proceeding.
Step 1: Load Configuration
Read the ## Arness section from CLAUDE.md. Extract the following fields:
- Plans directory -- where Arness project artifacts live (CHANGE_RECORD.json files, SWIFT_, STANDARD_, CATCHUP_* directories)
- Specs directory -- where spec files live (for boundary detection)
- Code patterns -- path to pattern documentation (for pattern refresh in Step 6)
- Template path -- path to report templates (for CATCHUP_REPORT_TEMPLATE.json)
- Template version -- plugin version the templates were copied from (if present)
- Template updates -- user preference:
ask,auto, ormanual(if present)
Template version check: If Template version and Template updates fields are present, run the template version check procedure documented in ${CLAUDE_PLUGIN_ROOT}/skills/arn-code-save-plan/references/template-versioning.md before proceeding. If ## Arness does not contain these fields, treat as legacy and skip.
Validate that all paths exist. If the plans directory does not exist, inform the user: "Plans directory not found. Run /arn-planning to set up Arness." and exit.
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.
- 2d ago First seen · 248 lines · 87 tokens per session scan A bef605478890
arn-code-catch-up is a skill published in the GitHub repository AppsVortex/arness (33 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 2,656 once invoked, about $0.0004 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.