speckit-companion: Command for Claude Code

.claude/commands/fix-tickets.md

fix-tickets is a command for Claude Code from alfredoperez/speckit-companion. It costs 49 tokens per session (6,987 once invoked), scanned A, original, MIT.

An automated workflow for fixing one or more GitHub issues in the SpecKit Companion project, then reviewing, testing, merging, reinstalling, and documenting the result. It can use the project's own specification workflow to fix each issue.

In plain words
What is it for?
Use it to process tickets through branches, code review, pull requests, squash merges, and a manual-verification report; a lighter mode handles small mechanical changes with parallel worktrees.
Why use it?
It coordinates the repeated steps of issue-based development and starts each fix from a clean, up-to-date installation. This helps avoid carrying errors from one ticket into the next.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

This is alfredoperez/speckit-companion's own configuration. It tells Claude Code how to work on speckit-companion itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything speckit-companion configures →

Reuse

Borrowing it

Nothing to install: this file belongs to alfredoperez/speckit-companion. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/alfredoperez/speckit-companion/main/.claude/commands/fix-tickets.md
Clone the repo
git clone --depth 1 https://github.com/alfredoperez/speckit-companion

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 fix-tickets

README.md
[![agentmods](https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/fix-tickets/github.svg)](https://agentmods.dev/commands/alfredoperez/speckit-companion/fix-tickets)
Your own site
<a href="https://agentmods.dev/commands/alfredoperez/speckit-companion/fix-tickets"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/fix-tickets/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-tickets

Your own site · 80×15
<a href="https://agentmods.dev/commands/alfredoperez/speckit-companion/fix-tickets"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/fix-tickets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,987 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 $0.00049 $0.06987
Opus 5 $0.00024 $0.03494
Sonnet 5 $0.00010 $0.01397
Haiku 4.5 $0.00005 $0.00699

Measured yesterday against content hash 4290d1d92372, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fix-tickets 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 yesterday.

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/fix-tickets.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What this does

A self-hosting build loop for speckit-companion. For each ticket, in strict sequence:

Two modes. The default (below) is the full loop: one issue per ticket, fixed by driving the SpecKit Companion pipeline on itself. --light (Light mode) drops the issue, the spec pipeline, and the sequencing for small mechanical changes, and fans out parallel worktree agents instead. It keeps the code review, tests, and CI. Light mode trades away the dogfooding signal — pick it deliberately, not by default.

  1. Clean slate + install-local FIRST — on main, git fetch && git pull --ff-only, then run /install-local so this ticket is fixed by the freshest build and the latest /speckit.companion.* commands (the previous ticket's merge lands here). Discard the throwaway version bump, assert a clean tree. Refuse to start dirty.
  2. Fix — drive the SpecKit Companion pipeline to fix the ticket.
  3. Code review — run /code-review, apply findings; re-run it on any fix that itself changed real logic.
  4. PR — open a PR with /create-pr conventions.
  5. Merge — squash-merge, delete branch.
  6. Capture learnings + tick the box — distill this ticket's review findings and route each to where it fires (review check → .claude/review-checklist.md; authoring convention → a proposed CLAUDE.md edit; loop mechanics → this file; gap → an issue candidate), so the next ticket's fix avoids the same bug class. Then check the ticket off in the vault's Current.md queue with its PR link.
  7. Next ticket — its step 1 /install-local installs this ticket's merge. After the last ticket, a closing /install-local installs the final merge. This is the point of the loop: prove the companion keeps working on itself as it improves.

After all tickets: write one run report (markdown, via the vault obsidian skill, into Projects/speckit companion/reports/) of everything fixed, in plain language, flagging UI / manual-test items so you know exactly what to verify by hand, what was already exercised by the pipeline (don't re-test), the new lessons captured, and any architecture/skill flags worth promoting. Use /html-page only to export it if it needs to leave the vault — HTML in the vault is unsearchable.

Read the full file on GitHub · 265 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. yesterday Changed · +6 lines 4290d1d92372
  2. 11d ago First seen · 259 lines · 49 tokens per session scan A b493e9e49ed7

Subscribe to this mod's changes

fix-tickets is a command published in the GitHub repository alfredoperez/speckit-companion (90 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 6,987 once invoked, about $0.0002 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.