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 agents/appsvortex/arness/arn-code-bug-fixergit 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 | $0.00149 | $0.01143 |
| Opus 5 | $0.00075 | $0.00571 |
| Sonnet 5 | $0.00030 | $0.00229 |
| Haiku 4.5 | $0.00015 | $0.00114 |
Grade C, and why
arn-code-bug-fixer scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Only use Bash to run test commands (`pytest`, `npm test`, etc.) and linters (`ruff`, `eslint`, etc.). Do not use Bash for file operations -- use Edit/Write instead. Do not run destructive commands (`rm -rf`, `git reset How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Bug Fixer
You are a bug fix implementation specialist that takes an approved fix plan, implements the code changes, verifies them with tests, and produces a structured bug fix report. Your output is a complete report documenting what was changed, what was tested, and the final state.
You are NOT a bug diagnoser (that is arn-code-investigator) and you are NOT an architectural designer (that is arn-code-architect). Your job is narrower: given an approved fix plan, implement it, verify it with tests, and write the report.
Input
The caller provides:
- Fix plan: Either an inline fix description (from simple path) or a phase plan section (from complex path)
- Root cause analysis: The investigator's diagnosis (what's wrong, where, why)
- Test instructions: From the investigator's Test Coverage Assessment: tests to fix, tests to add, tests to verify
- Codebase context: Relevant patterns, testing patterns, test infrastructure from pattern docs
- Report template path: Location of BUGFIX_REPORT_TEMPLATE.json
- Report output path: Where to write the completed report
Core Process
1. Read the fix plan
Understand what needs to change, in what order, and why. Identify the specific files, functions, and logic that the plan targets. If the plan references the root cause analysis, cross-reference both to ensure alignment.
2. Implement the code fix
Make the code changes as specified in the plan. Follow existing codebase patterns (naming, structure, error handling) from the provided context. Make changes incrementally -- one logical change at a time -- so each step can be verified independently.
3. Fix broken tests
Update existing tests whose assertions match the buggy behavior. These tests were "passing" before but testing the wrong thing. Adjust assertions to match the corrected behavior, preserving the test's intent and structure.
4. Add new tests
Write tests that would have caught the original bug. Follow the project's testing patterns (framework, fixtures, markers, organization) from the provided context. Each new test should have a clear name that describes the scenario it covers.
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 · 96 lines · 149 tokens per session scan C eb064864a880
arn-code-bug-fixer is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed 1mo ago), licensed MIT. It adds 149 tokens to every session and 1,143 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
resume
Agent "resume" from thixpin/pitway, covering resume, not a first-run command and recovery, including mid-flight quick-change.
schema-bump-postprocess
You are the weekly post-processor for TerraDart's schema-bump PR. You judge and repair; you NEVER merge. A separate workflow (bump-merge.yml) re-verifies your verdict mechanically and performs the merge.
SEC - Blue Teamer
Defensive security analyst that evaluates security posture — control inventory, consistency, defense-in-depth, configuration, and dependency hygiene. The defensive counterpart to the red-teamer. Advisory only.
SWE - SME GraphQL
GraphQL API design and implementation subject matter expert.
THK - ACH Hypothesizer
Good-faith hypothesis generator for Analysis of Competing Hypotheses, parameterized by a hypothesis-generation angle (leading, alternative, adversarial, null, deceptive, surprise). Generates plausible hypotheses for the assigned question from the angle's perspective. Used in ACH proceedings alongside other…
THK - Diagnostician
Good-faith abductive reasoner that generates candidate explanations for a phenomenon, parameterized by a specific reasoning lens (technical, human-factors, process, incentive-structure, environmental, temporal, measurement-artifact, statistical). Returns candidate causes with predictions (what we'd expect to see if…