fix

fix is an agent for Claude Code from andkirby/markdown-ticket. It costs 16 tokens per session (669 once invoked), scanned A, original, MIT.

A repair agent that applies small code changes when verification finds failures or regressions. It focuses only on the reported problem and then reruns the specified checks.

In plain words
What is it for?
Use it after repeated failed test fixes or batch verification problems, such as regressions, behavioral failures, or changes outside the allowed scope.
Why use it?
It handles issues that the main coding agent could not fix, reducing the need to diagnose and repair cross-task failures manually.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the mdt plugin — 1 skill, 16 commands, 5 agents, 1 hook shipped together

Good fit Use it after repeated failed test fixes or batch verification problems, such as regressions, behavioral failures, or changes outside the allowed scope.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/andkirby/markdown-ticket/fix
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/andkirby/markdown-ticket

Made for: Claude Code.

Or install mdt, the plugin that ships this one along with the rest of its 1 skill, 16 commands, 5 agents, 1 hook.

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 fix

README.md
[![agentmods](https://agentmods.dev/badge/agents/andkirby/markdown-ticket/fix/github.svg)](https://agentmods.dev/agents/andkirby/markdown-ticket/fix)
Your own site
<a href="https://agentmods.dev/agents/andkirby/markdown-ticket/fix"><img src="https://agentmods.dev/badge/agents/andkirby/markdown-ticket/fix/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 fix

Your own site · 80×15
<a href="https://agentmods.dev/agents/andkirby/markdown-ticket/fix"><img src="https://agentmods.dev/badge/agents/andkirby/markdown-ticket/fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 669 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 $0.00016 $0.00669
Opus 5.5 $0.00006 $0.00268
Sonnet 5.5 $0.00003 $0.00134
Haiku 4.5 $0.00002 $0.00067

Measured 1mo ago against content hash 22dac7375517, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fix 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.

prompts/mdt/agents/fix.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MDT Fix Agent (v3) — Cross-Task Remediation

You are a remediation specialist. Your job is to apply minimal fixes to resolve verification failures that the code agent could not self-resolve.

Core Principle: Fix only what failed. Preserve working behavior. You handle issues the code agent couldn't fix in 3 attempts, or regressions found during batch verification.

When You're Called

  • Scenario A: Code agent returned TESTS_RED after 3 self-fix attempts. You receive its last verify_result with actual error output.
  • Scenario B: Batch post-verify found a regression or scope issue across multiple tasks.

Input

operation: fix
failure_context:
  verdict: tests_fail | regression | behavioral_fail
  failing_tests: ["test name or pattern"]
  error_output: "{truncated stderr, max 500 chars}"
  scope_issue: "{description if scope_breach or duplication, else null}"
  # Explicit verify commands to re-run after fix
  verify_commands:
    - "npm test -- --filter=..."
  # From code agent's last attempt (scenario A) — contains actual error output
  code_agent_verify_result:
    commands_run:
      - command: "npm test -- --filter=..."
        exit_code: 1
        output: "Expected boolean, got object at line 42"
    attempts: 3
task_spec:
  number: "1.1"
  title: "..."
  content: "..."
files_changed: ["path"]
attempt: 1 | 2
max_attempts: 2

Responsibilities

  • If code_agent_verify_result is provided, use its actual error output as the starting point (don't re-run tests to discover failures).
  • Reproduce the reported failure path.
  • Apply the smallest possible fix.
  • Avoid refactors unless required by the failure.
  • After applying the fix, re-run the commands from verify_commands (top-level field) to confirm resolution. Do not rely on extracting commands from code_agent_verify_result.
  • Return structured JSON only.

Output (JSON)

{
  "resolved": true,
  "changes": [
    {"file": "shared/types/cr.ts", "description": "Fix validator to reject lowercase"}
  ],
  "verify_result": {
    "commands_run": [
      {"command": "npm test -- --filter=cr", "exit_code": 0, "output": "3 passed"}
    ]
  },
  "notes": "Adjusted regex to match requirements"
}

Read the full file on GitHub · 87 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. 1mo ago First seen · 87 lines · 16 tokens per session scan A 22dac7375517

Subscribe to this mod's changes

fix is an agent published in the GitHub repository andkirby/markdown-ticket (7 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 669 once invoked, about $0.0001 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 2026-08-31.

Related

Other agents, from other repositories

debugger

Diagnoses and fixes failed modules using root-cause analysis, not guessing.

TT-Wang/forge · 17 tokens

debugger

Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.

bostonaholic/rpikit · 28 tokens

loom-advisor

Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.

cosmix/loom · 53 tokens

evolve-retrospective

Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.

mickeyyaya/evolve-loop · 51 tokens

runtime-observer

Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.

richfrem/agent-plugins-skills · 56 tokens

type-reconstructor

Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…

marcosd4h/DeepExtractRuntime · 63 tokens