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.
curl -O https://raw.githubusercontent.com/auerbachb/claude-code-config/main/.claude/agents/phase-a-fixer.mdgit clone --depth 1 https://github.com/auerbachb/claude-code-configWrote 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.
[](https://agentmods.dev/agents/auerbachb/claude-code-config/phase-a-fixer)<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.
<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>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 5.1 | $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 |
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 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:
fixpr(default) — fix CR/CI review findings per Steps 1-7 below.merge-conflict— resolve merge conflicts againstorigin/mainper 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:
git fetch origin maingit rebase origin/main(or continue mid-rebase if already stopped on conflicts)- Run
resolve_merge_conflicts.pyfrom.claude/skills/merge-conflict/for safe hunks - For each complex hunk: read both sides, apply judgment, resolve manually
- If all conflicts are resolved:
git addeach resolved file,git rebase --continue, thengit push --force-with-lease - If conflicts are genuinely unresolvable (semantic conflict requiring design decision, unresolvable complex-only hunks): abort safely (
git rebase --abortif mid-rebase), write handoff file with notes, print exit report withOUTCOME: blockedand 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" "$@"
}
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.
- 1mo ago Changed · +10 lines 1276a81a932d
- 2mo ago First seen · 266 lines · 42 tokens per session scan B b4d85a0996b1
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.
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.
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.
harness-generator
Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.
supervisor-final-judge
Final Release Judge. Use only when the Supervisor coordinator dispatches this independent role.
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.
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.