A command that starts a structured plan for fixing a documented software defect. A regression is an existing behavior that must keep working after the fix.

Use it to document reproduction steps and constraints, analyze the codebase, design the fix, and create implementation tasks.

It records the observed and expected behavior, investigates likely causes, and plans a targeted fix with regression prevention.

spec-bugfix — Command by Habib0x0

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 commands/habib0x0/spec-driven-plugin/spec-bugfix

Clone the repo

git clone --depth 1 https://github.com/Habib0x0/spec-driven-plugin

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 561 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.

Model	Per session	Once invoked
Fable 5	$0.00020	$0.00561
Opus 5	$0.00010	$0.00280
Sonnet 5	$0.00004	$0.00112
Haiku 4.5	$0.00002	$0.00056

Measured 2d ago against content hash 70b18026f302, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-bugfix 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.

commands/spec-bugfix.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/spec-bugfix Command

Guide a bugfix through a three-phase workflow: Bug Analysis, Design, and Tasks.

Unlike feature specs which start from requirements, bugfix specs start from a documented defect and work toward a surgical fix with regression prevention.

Usage

/spec-bugfix <bug-name>

Arguments

Argument	Required	Description
`bug-name`	Yes	A short, kebab-case identifier for the bugfix. Used as the directory name.

Workflow

Phase 1: Bug Analysis

The agent guides the user through documenting the defect:

Current Behavior (Defect) — WHEN [condition] THEN the system [incorrect behavior]
Expected Behavior (Correct) — WHEN [condition] THEN the system SHALL [correct behavior]
Unchanged Behavior (Regression Prevention) — WHEN [condition] THEN the system SHALL CONTINUE TO [existing behavior]
Reproduction Steps — exact steps to reproduce the defect
Constraints — code that must not be modified, backward-compat requirements, etc.

The agent also performs automated root cause analysis by exploring the codebase around the defect.

Output: bugfix.md

Phase 2: Design

The agent proposes a fix approach:

Root cause summary
Proposed fix with minimal blast radius
Test properties to verify (reproducible, fixed, no regression)
Risk assessment

Output: design.md

Phase 3: Tasks

The agent breaks the fix into discrete tasks:

Reproduction test (confirms the bug exists)
Fix implementation (surgical change)
Regression tests (verify unchanged behavior still works)
Validation (confirm all three test properties pass)

Output: tasks.md

Directory Structure

.claude/specs/<bug-name>/
  bugfix.md      # Bug analysis with current/expected/unchanged behavior
  design.md      # Fix approach and test properties
  tasks.md       # Discrete implementation tasks

Tips

Be explicit about what code must NOT change — constraints prevent over-fixing
Document unchanged behavior carefully — this is what prevents regressions
The reproduction test should fail before the fix and pass after
Keep the fix surgical; resist the urge to refactor surrounding code

Read the full file on GitHub · 85 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.

2d ago First seen · 85 lines · 20 tokens per session scan A 70b18026f302

Subscribe to this mod's changes

spec-bugfix is a command published in the GitHub repository Habib0x0/spec-driven-plugin (10 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 561 once invoked, about $0.0001 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 2026-08-31.

Debugging Documents Writing and docs architecture claude claude-code claude-code-plugin codex codex-skill

spec-bugfix

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/spec-bugfix Command

Usage

Arguments

Workflow

Phase 1: Bug Analysis

Phase 2: Design

Phase 3: Tasks

Directory Structure

Tips

What this file has done since we first saw it

Other commands, from other repositories

receipts

ship

sruja-bugfix-triage

triage

smart-help

crossframe-essay