claude-code-config: Agent for Claude Code

.claude/agents/phase-a-fixer.md

phase-a-fixer is an agent for Claude Code from auerbachb/claude-code-config. It costs 42 tokens per session (4,065 once invoked), scanned B, original, MIT.

A coding agent that fixes findings from pull-request reviews or resolves merge conflicts, which happen when two code changes cannot be combined automatically. It commits and pushes the resulting changes and records a handoff.

In plain words
What is it for?
Use it after code review to fix reported problems, reply to review threads, or update a branch when it conflicts with the main branch.
Why use it?
It turns review comments and merge conflicts into a defined repair task with a clear completion report, instead of leaving fixes and follow-up work scattered.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

This is auerbachb/claude-code-config's own configuration. It tells Claude Code how to work on claude-code-config 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 claude-code-config configures →

Reuse

Borrowing it

Nothing to install: this file belongs to auerbachb/claude-code-config. 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/auerbachb/claude-code-config/main/.claude/agents/phase-a-fixer.md
Clone the repo
git clone --depth 1 https://github.com/auerbachb/claude-code-config

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 phase-a-fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/auerbachb/claude-code-config/phase-a-fixer/github.svg)](https://agentmods.dev/agents/auerbachb/claude-code-config/phase-a-fixer)
Your own site
<a href="https://agentmods.dev/agents/auerbachb/claude-code-config/phase-a-fixer"><img src="https://agentmods.dev/badge/agents/auerbachb/claude-code-config/phase-a-fixer/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 phase-a-fixer

Your own site · 80×15
<a href="https://agentmods.dev/agents/auerbachb/claude-code-config/phase-a-fixer"><img src="https://agentmods.dev/badge/agents/auerbachb/claude-code-config/phase-a-fixer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,065 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00042 $0.04065
Opus 5.5 $0.00017 $0.01626
Sonnet 5.5 $0.00008 $0.00813
Haiku 4.5 $0.00004 $0.00407

Measured 1mo ago against content hash 1276a81a932d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

phase-a-fixer scanned grade B with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

A repo-wide `find ~/.claude/handoffs -name 'pr-{{PR_NUMBER}}-handoff.json'` is

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Before leaving any work undone — whether you'd frame it as impossible, out of scope, a deployment step, or a runbook for someone else — walk the capability ladder for any provider CLI (`gh`, `git`, `curl`, or a service
.claude/agents/phase-a-fixer.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase A: Fix + Push

You are a Phase A subagent. Your job: read review findings or resolve merge conflicts (depending on the task type in your spawn prompt), fix the code, commit, push, reply to review threads, write a handoff file, and print an exit report. Then EXIT — do not enter a polling loop.

Task Types

The parent specifies one of these in your spawn prompt:

  1. fixpr (default) — fix CR/CI review findings per Steps 1-7 below.
  2. merge-conflict — resolve merge conflicts against origin/main per the Merge-Conflict Workflow below. Skip Steps 1-2 (findings) and Step 4-5 (thread reply/resolve) unless findings also exist after the rebase.

Merge-Conflict Workflow (when TASK_TYPE: merge-conflict)

Run the /merge-conflict skill workflow:

  1. git fetch origin main
  2. git rebase origin/main (or continue mid-rebase if already stopped on conflicts)
  3. Run resolve_merge_conflicts.py from .claude/skills/merge-conflict/ for safe hunks
  4. For each complex hunk: read both sides, apply judgment, resolve manually
  5. If all conflicts are resolved: git add each resolved file, git rebase --continue, then git push --force-with-lease
  6. If conflicts are genuinely unresolvable (semantic conflict requiring design decision, unresolvable complex-only hunks): abort safely (git rebase --abort if mid-rebase), write handoff file with notes, print exit report with OUTCOME: blocked and a prose reason above the report block, then EXIT — do NOT force-push a partial resolution

Stay within Safety Rules and the single-commit/push discipline where possible (one rebase resolution = one commit after rebase completes).

Resolving helper scripts (do this first)

You may be spawned against any repo, and most repos carry no .claude/ directory. Never invoke a bare .claude/scripts/<name> path — it silently does not exist outside the config repo. Define these once, then call every helper through run_script:

resolve_script() {
  local name="$1" candidate
  for candidate in \
    "$HOME/.claude/skills-worktree/.claude/scripts/$name" \
    "$HOME/.claude/scripts/$name" \
    ".claude/scripts/$name"; do
    if [[ -x "$candidate" ]]; then echo "$candidate"; return 0; fi
  done
  return 1
}

run_script() {            # run_script <name> [args...]
  local name="$1"; shift
  local script_path       # NOT `path`: zsh ties lowercase `path` to `PATH` (#1556)
  if ! script_path=$(resolve_script "$name"); then
    echo "ERROR: $name not found (checked ~/.claude/skills-worktree/.claude/scripts/, ~/.claude/scripts/, .claude/scripts/)" >&2
    return 127
  fi
  "$script_path" "$@"
}

Read the full file on GitHub · 276 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 Changed · +10 lines 1276a81a932d
  2. 2mo ago First seen · 266 lines · 42 tokens per session scan B b4d85a0996b1

Subscribe to this mod's changes

phase-a-fixer is an agent published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 4,065 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). 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

consistency-and-history

Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.

ncoevoet/claude-review-all · 34 tokens

historical-context-reviewer

Use this agent when reviewing local code changes or pull requests to understand the historical context of modified code, including past issues, patterns, and lessons learned. This agent should be invoked to prevent repeating past mistakes and to ensure consistency with previous decisions.

NeoLabHQ/context-engineering-kit · 54 tokens

harness-generator

Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.

stone16/harness-engineering-skills · 29 tokens

supervisor-final-judge

Final Release Judge. Use only when the Supervisor coordinator dispatches this independent role.

ma-nucho-pro/supervisor-claude-plugin · 22 tokens

pr-creator

Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.

axiomantic/spellbook · 75 tokens

test-reviewer

Review-only agent for test quality — whether tests protect critical behavior and catch realistic regressions; mock/fixture drift, test layering, missing critical scenarios. P0–P2.

akholod/consensus-review · 40 tokens