sruja-bugfix-triage

sruja-bugfix-triage is a command for Claude Code, Cursor from sruja-ai/sruja. It costs 0 tokens per session (522 once invoked), scanned A, original, Apache-2.0.

A structured workflow for investigating and fixing software bugs. It reproduces the problem, identifies affected components, proposes a small fix, applies it, and verifies the result.

In plain words
What is it for?
Use it to triage bugs, understand their impact, create a focused fix plan, implement the fix, and verify it with a bug-fix profile.
Why use it?
It gives bug fixing a repeatable path from failure to tested change. It also checks for similar past issues and limits the fix to the smallest useful change.

Command for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code command (commands/*.md). Also seen: mentions AGENTS.md.

Good fit Use it to triage bugs, understand their impact, create a focused fix plan, implement the fix, and verify it with a bug-fix profile.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/sruja-ai/sruja/sruja-bugfix-triage
Install

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.

Clone the repo
git clone --depth 1 https://github.com/sruja-ai/sruja

Made for: Claude Code, Cursor.

Wrote 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.

agentmods badge for sruja-bugfix-triage

README.md
[![agentmods](https://agentmods.dev/badge/commands/sruja-ai/sruja/sruja-bugfix-triage/github.svg)](https://agentmods.dev/commands/sruja-ai/sruja/sruja-bugfix-triage)
Your own site
<a href="https://agentmods.dev/commands/sruja-ai/sruja/sruja-bugfix-triage"><img src="https://agentmods.dev/badge/commands/sruja-ai/sruja/sruja-bugfix-triage/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.

agentmods 80×15 button for sruja-bugfix-triage

Your own site · 80×15
<a href="https://agentmods.dev/commands/sruja-ai/sruja/sruja-bugfix-triage"><img src="https://agentmods.dev/badge/commands/sruja-ai/sruja/sruja-bugfix-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 522 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00522
Opus 5 $0.00000 $0.00261
Sonnet 5 $0.00000 $0.00104
Haiku 4.5 $0.00000 $0.00052

Measured 10d ago against content hash 7126e9276351, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sruja-bugfix-triage 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 10d 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.

.cursor/commands/sruja-bugfix-triage.md · 67 lines

What it actually says

Sruja: Bugfix Triage

Systematic workflow for triaging and fixing bugs with architecture grounding.

Related: plan-featureimplement-from-planverify-taskreflect-on-run

Steps

  1. Reproduce the bug

    • Understand the failure mode
    • Identify the affected file(s) and component(s)
  2. Get focus briefing

    sruja focus --file <buggy-file> -r . -f for-ai
    

    This gives you the blast radius, decisions, and AI instructions for the target.

  3. Search memory for similar issues

    sruja agent history -r . -f json
    # Or MCP: sruja_search_memory with the error message
    

    Check if this bug (or similar) has been encountered before.

  4. Form a hypothesis

    • What component is broken?
    • What change would fix it?
    • What's the blast radius of the fix?
  5. Create a minimal fix plan

    • Scope the change to the smallest possible diff
    • Identify which verification steps will validate the fix
  6. Implement the fix

    • Make the minimal change
    • Do not refactor unrelated code
  7. Verify with bugfix profile

    sruja verify-task --profile bugfix --file <buggy-file> -r .
    
  8. If verify fails:

    • Review the failed step
    • Fix and re-verify
    • Record a correction learning
  9. If verify passes:

    • Optionally record an affirmation learning
    • Mark the bug as fixed

Example

# Bug: auth token validation fails on edge cases
sruja focus --file src/auth/token.rs -r . -f for-ai
sruja agent history -r . -f json  # Check for similar auth bugs
# ... implement fix ...
sruja verify-task --profile bugfix --file src/auth/token.rs -r .

References

Changes

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.

  1. 10d ago First seen · 67 lines · 0 tokens per session scan A 7126e9276351

Subscribe to this mod's changes

sruja-bugfix-triage is a command published in the GitHub repository sruja-ai/sruja (24 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 522 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 2026-08-30.