Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add AppsVortex/arness/plugin install arn-codeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/appsvortex/arness/arn-code-bug-spec)<a href="https://agentmods.dev/skills/appsvortex/arness/arn-code-bug-spec"><img src="https://agentmods.dev/badge/skills/appsvortex/arness/arn-code-bug-spec/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/appsvortex/arness/arn-code-bug-spec"><img src="https://agentmods.dev/badge/skills/appsvortex/arness/arn-code-bug-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00119 | $0.02971 |
| Opus 5.5 | $0.00048 | $0.01188 |
| Sonnet 5.5 | $0.00024 | $0.00594 |
| Haiku 4.5 | $0.00012 | $0.00297 |
Grade A, and why
arn-code-bug-spec 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 1mo 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Bug Spec
Investigate a bug through iterative conversation, aided by diagnostic analysis from the arn-code-investigator agent, architectural validation from the arn-code-architect agent, and optional automated fix execution from the arn-code-bug-fixer agent. Every bug investigation gets its own project folder (BUGFIX_<name>/) in the plans directory. For simple bugs, the artifact is a fix plus a bug fix report. For complex bugs, the artifact is a bug specification written to .arness/specs/ that informs plan creation via the /arn-code-plan skill.
This is a conversational skill. It runs in normal conversation (NOT plan mode). A BUGFIX_<name>/ project folder is created at the start of every investigation. For simple bugs, the folder holds the fix report. For complex bugs, a specification document is written to <specs-dir>/BUGFIX_<name>.md, and the project folder is used later by arn-code-save-plan after the plan is generated via /arn-code-plan.
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.
Workflow
Step 1: Capture the Bug Report
Accept the user's bug description. This can be anything from "X is broken" to a detailed report with stack traces, error messages, and reproduction steps. Do not require a specific format.
If the user already provided the bug description in their trigger message (e.g., "bug spec: users are getting 500 errors on checkout"), use that directly without asking again.
Acknowledge the report with a brief restatement to confirm understanding. Ask targeted follow-up questions ONLY if critical information is missing:
- What is expected vs actual behavior?
- Any error messages or stack traces?
- When did it start? (recent change, always broken, intermittent)
Do NOT require answers to all of these. Work with what is available and proceed.
What ships with it
4 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.
- 1mo ago First seen · 204 lines · 119 tokens per session scan A 61c86846de79
arn-code-bug-spec is a skill published in the GitHub repository AppsVortex/arness (33 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 2,971 once invoked, about $0.0005 per session on Opus 5.5. 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
pulumi-debug-failed-operation
Debug a Pulumi update or preview that failed: read the failure Pulumi already recorded, find what caused it, and fix it. Load this skill when the user asks to debug, diagnose, or fix a failed update or preview, or points at a failing pulumi up or pulumi preview. Don't load it for authoring new infrastructure…
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
bug-fixer
A bug reproduces, the expected behaviour is clear, and the fix stands apart from the current work.
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.
git-investigate
Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report.