speckit.fix

speckit.fix is a command for Claude Code from jmanhype/speckit. It costs 24 tokens per session (758 once invoked), scanned A, original, MIT.

A quick-fix command for small, targeted code or documentation changes that have an obvious solution. It checks the request's scope, applies the minimal change, and runs verification.

In plain words
What is it for?
Use it for typo corrections, style changes, missing imports, lint errors, small refactors, documentation fixes, and configuration tweaks.
Why use it?
It avoids using a full feature-planning process for simple maintenance work. It also flags requests that are too broad or risky for a quick fix.

Command for Claude Code

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/jmanhype/speckit/speckit.fix
Clone the repo
git clone --depth 1 https://github.com/jmanhype/speckit

Made for: Claude Code.

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 speckit.fix

README.md
[![agentmods](https://agentmods.dev/badge/commands/jmanhype/speckit/speckit.fix.svg)](https://agentmods.dev/commands/jmanhype/speckit/speckit.fix)
Your own site
<a href="https://agentmods.dev/commands/jmanhype/speckit/speckit.fix"><img src="https://agentmods.dev/badge/commands/jmanhype/speckit/speckit.fix.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 758 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 $0.00024 $0.00758
Opus 5 $0.00012 $0.00379
Sonnet 5 $0.00005 $0.00152
Haiku 4.5 $0.00002 $0.00076

Measured 3d ago against content hash 4b77192c4477, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speckit.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 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.

.claude/commands/speckit.fix.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quick Fix Command

User Input

$ARGUMENTS

Purpose

This command is for simple, targeted fixes that don't warrant the full specify → plan → tasks → implement workflow.

Use this for:

  • Typo fixes
  • Color/style changes
  • Simple bug fixes with obvious solutions
  • Adding missing imports
  • Fixing linting errors
  • Small refactors (rename variable, extract function)
  • Documentation typos
  • Configuration tweaks

Do NOT use this for:

  • New features (use /speckit.specify)
  • Architectural changes (use full workflow)
  • Security fixes (need proper review)
  • Changes affecting multiple systems
  • Anything requiring design decisions

Workflow

  1. Parse the fix request from $ARGUMENTS

  2. Validate scope - If the fix seems complex, recommend full workflow:

    This fix appears to require architectural decisions.
    Consider using /speckit.specify instead.
    
  3. Locate the issue:

    • Search codebase for relevant files
    • Identify the specific location(s) to change
  4. Apply the fix:

    • Make the minimal change required
    • Follow project-standards skill (invoke if needed for guidance)
    • Ensure tests still pass (test-gate.sh will run automatically)
  5. Verify:

    • Confirm the fix addresses the issue
    • Check no regressions introduced
  6. Report:

    ## Fix Applied
    
    **Issue**: [Brief description]
    **Files Changed**:
    - `path/to/file.ext` (line X)
    
    **Change Summary**: [What was changed]
    
    **Tests**: ✓ Passing
    

Beads Integration (Optional)

If this fix relates to an existing Beads issue:

# Link to existing issue
bd note <issue-id> "Quick fix applied: $ARGUMENTS"

# Or create a new issue if worth tracking
bd create "Fix: $ARGUMENTS" --type bug --status done

Examples

Example 1: Typo Fix

/speckit.fix Fix typo in README: "recieve" should be "receive"

Example 2: Style Change

/speckit.fix Change primary button color from blue to green

Read the full file on GitHub · 124 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 · 124 lines · 24 tokens per session scan A 4b77192c4477

Subscribe to this mod's changes

speckit.fix is a command published in the GitHub repository jmanhype/speckit (26 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 758 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 2026-09-01.