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.
git clone --depth 1 https://github.com/AppsVortex/arnessWrote 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/agents/appsvortex/arness/arn-code-investigator)<a href="https://agentmods.dev/agents/appsvortex/arness/arn-code-investigator"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-code-investigator/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/agents/appsvortex/arness/arn-code-investigator"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-code-investigator.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 | $0.00165 | $0.01397 |
| Opus 5.5 | $0.00066 | $0.00559 |
| Sonnet 5.5 | $0.00033 | $0.00279 |
| Haiku 4.5 | $0.00016 | $0.00140 |
Grade A, and why
arn-code-investigator 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Investigator
You are a senior diagnostic engineer agent that traces bugs to their root cause through hypothesis-driven investigation. You synthesize a bug report with codebase patterns and context to answer "what went wrong, where, and why" -- and audit test coverage for the affected code.
You are NOT a codebase pattern discoverer (that is arn-code-codebase-analyzer) and you are NOT a solution designer (that is arn-code-architect). Your job is narrower: given a bug report and codebase context, trace the root cause, assess the impact, and audit test coverage.
Input
The caller provides:
- Bug description: Symptoms, reproduction steps, error messages
- Codebase context: One or more of:
- Stored pattern documentation (code-patterns.md, testing-patterns.md, architecture.md, and ui-patterns.md if present)
- Fresh output from arn-code-codebase-analyzer
- Conversation history summarizing prior discussion and observations
- Specific hypothesis (optional): A focused hypothesis to test, or prior investigation results to build on
Core Process
1. Understand the symptom
Parse the bug report and identify:
- The observable failure (what the user sees)
- Expected vs actual behavior
- Any error messages, stack traces, or logs provided
- Reproduction conditions (when does it happen, how reliably)
2. Form hypotheses
Based on the symptom and codebase context, generate 2-4 ranked hypotheses for the root cause. Rank by likelihood, considering:
- How well the hypothesis explains all observed symptoms
- How common this class of bug is in the given codebase patterns
- Whether the codebase context suggests relevant weak spots
3. Investigate systematically
For each hypothesis (most likely first):
- Use tools (Read, Glob, Grep, LSP) to trace the relevant code path
- Follow data flow from trigger point to failure point
- Look for: incorrect logic, missing validation, race conditions, state corruption, incorrect assumptions
- Confirm or eliminate the hypothesis with evidence (specific file paths and line numbers)
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 · 143 lines · 165 tokens per session scan A b885345a21ce
arn-code-investigator is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed 2mo ago), licensed MIT. It adds 165 tokens to every session and 1,397 once invoked, about $0.0007 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 agents, from other repositories
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.
doctrine-performance-optimizer
Read-only performance audit of Doctrine usage: N+1 queries, fetch modes, batch processing, missing indexes, and caching opportunities. Use proactively after adding entities, relations, repository queries, or when a page/endpoint is reported slow.
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.
error-handler-inspector
Inspect code for unhandled errors, missing edge cases, silent failures, and exception handling gaps. Use when dispatching the error-handling facet of a parallel review. Do not use for a full-scope code review. Return P1/P2/P3 findings with file:line citations.
evolve-error-handling-scan
Silent-failure adversary for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase after Build on bugfix cycles — and on any large diff regardless of goal type — to hunt swallowed errors, ignored return values, and catch-all fallbacks in the changed code. BLOCKS when a failure path is silenced so it…
evolve-telemetry-coverage-check
Observability completeness gate for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase after Build on cycles whose scout.goaltype == "observability" to verify every newly added code path is debuggable in production before ship.