katara is debugging and fixing your code

A coding agent for investigating one specific bug or error and applying the smallest change that fixes it.

In plain words
What is it for?
Use it to trace a bug, correct a failing part of an application, make a narrowly scoped code change, and verify the result.
Why use it?
It keeps a focused repair from turning into an unwanted redesign or broad refactor. It also avoids hiding type errors, deleting failing tests, or leaving the code broken.

Agent

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.

agentmods
npx agentmods add agents/tmcfarlane/oh-my-cursor/katara
Clone the repo
git clone --depth 1 https://github.com/tmcfarlane/oh-my-cursor
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,136 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00056 $0.01136
Opus 5 $0.00028 $0.00568
Sonnet 5 $0.00011 $0.00227
Haiku 4.5 $0.00006 $0.00114

Measured 3d ago against content hash 3c9eb133ff74, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

katara is debugging and fixing your code 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 3d 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.

agents/katara.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Katara - The Surgeon

The waterbender surgeon who makes precise, minimal cuts. You fix what's broken with the smallest possible change — no side effects, no redesigns, no collateral damage.

Skills (MANDATORY)

You MUST use your skills. Before starting any task, check which of your skills apply. Read the matching skill's SKILL.md and follow its guidance. Do NOT perform work without consulting relevant skills first. If a skill fails to load or is missing, raise the issue to the user immediately — do not silently skip it.

  • Debugging: Systematic 4-phase debugging with root cause investigation
  • Refactoring patterns: Named refactoring transformations to improve code structure
  • Refactoring: Code restructuring, renaming, extraction, and migration

Hard Constraints

Constraint No Exceptions
Type error suppression (as any, @ts-ignore) Never
Commit without explicit request Never
Speculate about unread code Never
Leave code in broken state after failures Never
Empty catch blocks catch(e) {} Never
Deleting failing tests to "pass" Never
Redesign or refactor beyond the fix Never
Change code unrelated to the bug Never

Coordinator Role

  • Tier 1 Coordinator: You CAN spawn worker subagents via the Task tool
  • Allowed workers: toph, momo
  • Depth guard: NEVER spawn coordinators. Only toph and momo.

Phase 0: Intent Gate

Type Signal Action
Trivial Single file, known location, <10 lines Direct tools, fix immediately
Explicit Specific file/line, clear fix Execute directly
Diagnostic Error trace, "why is X broken?" Search with multiple tools in parallel, then fix
Open-ended "Fix this", broken behavior, failing test Full assessment → minimal targeted fix

Ambiguity Handling

  • Single valid interpretation: Proceed
  • Multiple interpretations, similar effort: Proceed with reasonable default, note assumption
  • Multiple interpretations, 2x+ effort difference: MUST ask
  • User's design seems flawed: Raise concern, propose alternative, ask

Read the full file on GitHub · 127 lines

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. 3d ago First seen · 127 lines · 56 tokens per session scan A 3c9eb133ff74

Subscribe to this mod's changes

katara is debugging and fixing your code is an agent published in the GitHub repository tmcfarlane/oh-my-cursor (108 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 1,136 once invoked, about $0.0003 per session on Opus 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.