fix

fix is a command for Claude Code from ANcpLua/ancplua-claude-plugins. It costs 85 tokens per session (2,658 once invoked), scanned A, original, MIT.

A gated bug-fixing workflow with four stages: finding the cause, designing a solution, changing the code, and checking the result. TDD, or test-driven development, means writing or updating tests as part of the implementation process.

In plain words
What is it for?
Use it to resolve a reported bug at a chosen severity, with optional parallel analysis and final build, test, and lint checks.
Why use it?
It separates investigation from changes and stops later stages when an earlier decision or check fails.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the TodoWrite tool; positional $N argument.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the exodia plugin — 2 skills, 7 commands shipped together

Good fit Use it to resolve a reported bug at a chosen severity, with optional parallel analysis and final build, test, and lint checks.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ANcpLua/ancplua-claude-plugins
Claude Code
/plugin install exodia

Made for: Claude Code.

Or install exodia, the plugin that ships this one along with the rest of its 2 skills, 7 commands.

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/commands/ancplua/ancplua-claude-plugins/fix/github.svg)](https://agentmods.dev/commands/ancplua/ancplua-claude-plugins/fix)
Your own site
<a href="https://agentmods.dev/commands/ancplua/ancplua-claude-plugins/fix"><img src="https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/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/commands/ancplua/ancplua-claude-plugins/fix"><img src="https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,658 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 $0.00085 $0.02658
Opus 5.5 $0.00034 $0.01063
Sonnet 5.5 $0.00017 $0.00532
Haiku 4.5 $0.00009 $0.00266

Measured 14d ago against content hash f9c4adc2649d, 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 14d 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.

plugins/exodia/commands/fix.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FIX — Gated Bug Resolution Pipeline

Execute → Evaluate → Decide. Every phase a gate. Every gate a verdict.

Issue: $0 Severity: $1 (default: P1 | P0|P1|P2|P3) Parallelism: $2 (default: standard | maximum|standard) Mode: $3 (default: balanced | aggressive|balanced|conservative) Quick: $4 (default: false — skip devil's advocate)


TEAM ARCHITECTURE

FIX LEAD (You — Orchestrator)
│
├─ Phase 1: ANALYSIS (standard: 3, maximum: 6)
│  ├── root-cause-hunter
│  ├── impact-assessor
│  ├── code-explorer
│  ├── history-detective       ← maximum only
│  ├── pattern-matcher         ← maximum only
│  └── test-analyzer           ← maximum only
│  └── GATE 1 → PROCEED | HALT
│
├─ Phase 2: DESIGN (standard: 2, maximum: 4)
│  ├── solution-architect[-a/-b/-c]
│  └── devils-advocate         ← skip if $4=true
│  └── GATE 2 → PROCEED | HALT
│
├─ Phase 3: IMPLEMENTATION (standard: 1, maximum: 2)
│  ├── tdd-implementer         ← atomic: owns tests AND code
│  └── docs-updater            ← maximum only
│  └── GATE 3 → PROCEED | HALT
│
└─ Phase 4: VERIFICATION (direct — no agents)
   └── Build + Test + Lint → FIXED | BLOCKED

<CRITICAL_EXECUTION_REQUIREMENT>

STEP -1 — Inherit Prior Findings: If <EXODIA_FINDINGS_CONTEXT> tag exists in session context, read .eight-gates/artifacts/findings.json. Filter by finding.id matching $0. If a match exists, inject its fix, files, and severity into Phase 1 agent prompts as pre-existing context. Skip re-discovery of already-known information.

YOU ORCHESTRATE. AGENTS FIX.

  1. Launch Phase 1 agents in ONE message (Task tool, parallel)
  2. Evaluate GATE 1
  3. Launch Phase 2, evaluate GATE 2
  4. Launch Phase 3, evaluate GATE 3
  5. Run Phase 4 verification directly
  6. Present summary

DO NOT ask "should I continue?" between phases. ONLY STOP if: build fails, tests fail, or unrecoverable error.

YOUR NEXT MESSAGE: Launch Phase 1 Task tool calls. NOTHING ELSE.

</CRITICAL_EXECUTION_REQUIREMENT>

Read the full file on GitHub · 365 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. 14d ago First seen · 365 lines · 85 tokens per session scan A f9c4adc2649d

Subscribe to this mod's changes

fix is a command published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 3d ago), licensed MIT. It adds 85 tokens to every session and 2,658 once invoked, about $0.0003 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 2026-10-01.