fixpr

A procedure for cleaning up a pull request, a proposed code change submitted for review. It checks review discussions and automated tests, fixes reported issues, pushes updates, and repeats the review cycle up to five times.

In plain words
What is it for?
Use it to process pull-request review comments, repair failing CI checks, resolve review threads, reply to findings, wait for new automated reviews, and report any remaining work.
Why use it?
It keeps fixes, review replies, resolved discussions, and test results together, reducing the chance that an old comment or failed check is left behind before merging.

Skill for Claude CodeCodex

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 skills/auerbachb/claude-code-config/fixpr
Any agent
npx skills add auerbachb/claude-code-config --skill fixpr
Clone the repo
git clone --depth 1 https://github.com/auerbachb/claude-code-config

Made for: Claude Code, Codex.

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 18,385 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 $0.00088 $0.18385
Opus 5 $0.00044 $0.09192
Sonnet 5 $0.00018 $0.03677
Haiku 4.5 $0.00009 $0.01838

Measured 2d ago against content hash 7bedcf36f086, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fixpr 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.

The scan reads SKILL.md. This mod also ships 1 executable file (audit.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/fixpr/SKILL.md · 938 lines

How it starts

The opening of the file, as written. The whole thing — 938 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bounded-convergence cleanup of the current branch's PR (issue #454 added the post-push review-wait loop to the original single-pass design). After this completes:

  1. Zero uncollapsed review threads in the browser (all resolved via GraphQL)
  2. Zero failing CI checks (all fixed and passing)
  3. Every finding replied to with what was done
  4. A definitive bot verdict on the final SHA — or an explicit cap-hit report naming what is still pending (never a silent "we pushed, bye" exit)

Portable helper resolution

Resolve the helpers used by executable examples before Step 0. The handoff-path helper has a documented legacy fallback; every write/safety helper is required.

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
}
PR_AUTHORSHIP_SH=$(resolve_script pr-authorship.sh || true)
HANDOFF_STATE_SH=$(resolve_script handoff-state.sh || true)
REPLY_THREAD_SH=$(resolve_script reply-thread.sh || true)
RESOLVE_REVIEW_THREADS_SH=$(resolve_script resolve-review-threads.sh || true)
DIFF_SURVIVAL_SH=$(resolve_script diff-survival-check.sh || true)
LOCAL_REVIEW_SH=$(resolve_script local-review.sh || true)
CLEAN_BEHIND_SH=$(resolve_script clean-behind-check.sh || true)
ADMIN_MERGE_SH=$(resolve_script admin-merge.sh || true)
MERGE_GATE_SH=$(resolve_script merge-gate.sh || true)
[[ -n "$PR_AUTHORSHIP_SH" ]] || { echo "ERROR: pr-authorship.sh not found (checked all three paths) — fix workflow authorship gate unavailable" >&2; exit 1; }
[[ -n "$REPLY_THREAD_SH" ]] || { echo "ERROR: reply-thread.sh not found (checked all three paths) — review replies unavailable" >&2; exit 1; }
[[ -n "$RESOLVE_REVIEW_THREADS_SH" ]] || { echo "ERROR: resolve-review-threads.sh not found (checked all three paths) — thread resolution unavailable" >&2; exit 1; }
[[ -n "$DIFF_SURVIVAL_SH" ]] || { echo "ERROR: diff-survival-check.sh not found (checked all three paths) — rebase survival gate unavailable" >&2; exit 1; }
[[ -n "$LOCAL_REVIEW_SH" ]] || { echo "ERROR: local-review.sh not found (checked all three paths) — local review unavailable" >&2; exit 1; }
[[ -n "$CLEAN_BEHIND_SH" ]] || { echo "ERROR: clean-behind-check.sh not found (checked all three paths) — clean-BEHIND verification unavailable" >&2; exit 1; }
[[ -n "$ADMIN_MERGE_SH" ]] || { echo "ERROR: admin-merge.sh not found (checked all three paths) — clean-BEHIND recovery unavailable" >&2; exit 1; }
[[ -n "$MERGE_GATE_SH" ]] || { echo "ERROR: merge-gate.sh not found (checked all three paths) — residual merge verification unavailable" >&2; exit 1; }
if [[ -z "$HANDOFF_STATE_SH" ]]; then
  echo "DEGRADED: handoff-state.sh not found (checked all three paths) — namespaced handoff path unavailable, continuing with legacy flat path" >&2
fi

Read the full file on GitHub · 938 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 938 lines · 88 tokens per session scan A 7bedcf36f086

Subscribe to this mod's changes

fixpr is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 3d ago), licensed MIT. It adds 88 tokens to every session and 18,385 once invoked, about $0.0004 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.