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-implementingnpx skills add AppsVortex/arness --skill arn-implementinggit 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 | $0.00138 | $0.04194 |
| Opus 5 | $0.00069 | $0.02097 |
| Sonnet 5 | $0.00028 | $0.00839 |
| Haiku 4.5 | $0.00014 | $0.00419 |
Grade A, and why
arn-implementing 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 — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Implementing
Execute an implementation plan, run a quick implementation (swift), run a standard-tier implementation, or manage the build-simplify-review cycle. This is a first-citizen entry point that orchestrates arn-code-execute-plan, arn-code-swift, arn-code-standard, arn-code-simplify, arn-code-review-implementation, and related execution skills. Chains from arn-planning and chains to arn-shipping or arn-assessing at completion.
This skill is a sequencer and decision-gate handler. It MUST NOT duplicate sub-skill logic. All implementation work is done by the invoked skills. Arness-implementing handles: input routing, state detection, execution mode selection, the simplify/review cycle, and chaining.
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.
After Step 0 completes, extract the following from ## Arness:
- Plans directory — for detecting structured plans and project folders
- Code patterns — path to stored pattern documentation
- Template path — path to report templates
Workflow
Step 0: Input Routing
Check the trigger message for swift or standard intent:
-
"swift: [description]", "quick: [description]", "quick change: [description]", or "quick implementation: [description]" detected: → Route directly to the Swift Path (Step S1). Skip all state detection.
-
"standard: [description]" or "standard mode: [description]" detected: → Route directly to the Standard Path (Step ST1). Skip all state detection.
-
No swift or standard intent detected: → Proceed to Step 1 (State Detection).
Step 1: State Detection
Check which artifacts exist on disk to determine the entry point. Check from most advanced to least advanced — first match wins:
| Artifact | Detected State | Resume Point |
|---|---|---|
SIMPLIFICATION_REPORT.json in <plans-dir>/<project>/reports/ |
Simplification done | G4 (Review implementation) |
Any IMPLEMENTATION_REPORT_*.json or TESTING_REPORT_*.json in <plans-dir>/<project>/reports/ (no SIMPLIFICATION_REPORT) |
Execution complete | G3 (Simplify?) |
TASKS.md in <plans-dir>/<project>/ with parseable task entries |
Tasks exist | G2 (Execution mode) |
INTRODUCTION.md in <plans-dir>/<project>/ but no TASKS.md |
Plan saved, not taskified | Auto-taskify, then G2 |
SWIFT_REPORT.json in <plans-dir>/SWIFT_<name>/ |
Swift complete | G5 (Completion handoff) |
<plans-dir>/SWIFT_<name>/SWIFT_<name>.md but no report |
Swift plan exists, not executed | Resume swift execution |
STANDARD_REPORT.json in <plans-dir>/STANDARD_<name>/ |
Standard complete | G5 (Completion handoff) |
<plans-dir>/STANDARD_<name>/STANDARD_<name>.md but no report |
Standard in progress | Resume standard execution |
| None of the above | No plan found | G0 (No plan fallback) |
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 · 373 lines · 138 tokens per session scan A c34d7185bdb0
arn-implementing is a skill published in the GitHub repository AppsVortex/arness (33 stars, last pushed 1mo ago), licensed MIT. It adds 138 tokens to every session and 4,194 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
add-app-clip
Add an iOS App Clip target to an Expo app. Use when the user mentions App Clip, AASA, apple-app-site-association, appclips, smart app banner, or wants to ship a lightweight iOS Clip invoked from a URL alongside their parent app.
agent-qa-authoring
Create, edit, validate, and run Agent QA tests, suites, and hooks through MCP or CLI while preserving canonical IDs and schema contracts.
accessibility-compliance-accessibility-audit
You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct audits, identify barriers, and provide remediation guidance.
terradart-add-curated-resource
Add or update a curated Google Cloud factory via terradart wrap (schema.json, optional MM YAML, wrapper override, lint, regenerate). Use when extending terradartgoogle with a new google resource.
terradart-add-beta-resource
Add a beta-only curated factory to terradartgooglebeta (filtered-fixture extraction, googlebeta override, wrap with provider pin). Use when a later provider pin introduces a new beta-only google type — the current pin's beta-only catalog is filled.
terradart-backfill-examples
Backfill example quickstarts for curated factories listed in tool/exampledebt.yaml — extend stacks, sync debt, and run terraform validate locally before PR.