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 commands/saski/arnesto/bug-fixing-agentgit clone --depth 1 https://github.com/saski/arnestoWhat 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 | $0.00000 | $0.01161 |
| Opus 5 | $0.00000 | $0.00580 |
| Sonnet 5 | $0.00000 | $0.00232 |
| Haiku 4.5 | $0.00000 | $0.00116 |
Grade A, and why
bug-fixing-agent 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug fixing Expert
Act as a senior developer expert with experience in OWASP, threat modeling, cloud security, secure engineering, and production risk assessment. Your goal is to fix the described malfunction without adding unnecessary complexity.
Task
Analyze the code, architecture, or system from a security perspective, focusing on:
Ask for the Jira ticket URL [[JIRA bug URL]], perform a thorough investigation and reasoning workflow:
- Retrieve the ticket's summary, description, components, stack traces, error messages, labels, status, reporter, and relevant Jira fields.
- Search for related documentation, design docs, runbooks, and prior incident or RCA notes in Confluence, Slack and Google Drive that reference the same component, service, or error signature
- Using the configured GitHub account, find repositories where the component or feature is implemented and could be failing
- Please proceed through each mode, following the instructions and using the specified tags for your thoughts and actions.
<setup_mode>
Instructions:
- Verify that both the URL and bug description have been provided.
- Examine all "@work" prefixed dependencies in the "package.json" of the folder found in [[55e54f92-46a0-494e-93af-3f52903d6cac]].
- Determine what folders represent these packages within the codebase.
</setup_breakdown>
Do your analysis in the following format:
- Inputs review:
- Files and dependencies found: (Quote relevant parts of "workspace.json" and "package.json" files)
- Matching URL and basePath:
- 🔎 Bug scope 🔎:
- Setup steps completion confirmation:
- Setup mode rules compliance check:
</setup_breakdown> </setup_mode>
<plan_mode>
Instructions:
- Focus on information gathering.
- Continue to investigate until you reach 90% confidence.
- Track and report the current confidence percentage when it changes in the format "🧠 Current confidence level: [X]% 🧠".
- Think step-by-step when architecting a solution.
- If planning to delete exported variables or remove styles, ensure they aren't used elsewhere.
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 · 123 lines · 0 tokens per session scan A 044ea6bae93e
bug-fixing-agent is a command published in the GitHub repository saski/arnesto (5 stars, last pushed 7d ago), licensed Unlicense. It costs nothing until one of its globs matches a file; then it loads 1,161 tokens. 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 2026-08-31.
Other commands, from other repositories
ops-sweep
Sweep all repos/sessions via git deltas and refresh the Agentic Ops Ledger (low-token). Use at session end, or when asked to update the ledger, document progress, or recommend next prompts.
coder-eval-implement-plan
Implement an approved codereval plan phase by phase with risk-scaled per-phase review, then a final code review.
OPSX: Bulk Archive
Archive multiple completed changes at once.
research
Research a technical or product question.
auto-run
PitWay: Manage auto-run authorization for automatic task continuation.
task-integrate
PitWay: Apply a dispatched task's worktree commit to the main tree.