fix-pr-commit-titles

fix-pr-commit-titles is a skill for Claude Code, Codex from Jessinra/Lorekeeper. It costs 38 tokens per session (1,008 once invoked), scanned A, original, Apache-2.0.

A Git tool for changing many commit titles on a pull request branch to the required format in one operation.

In plain words
What is it for?
Use it when commit titles on a GitHub pull request do not follow the project's `[LKPR-number] type: description` format.
Why use it?
It avoids editing commits one by one, which can repeatedly run checks and fail because of old lint problems. Rewriting commits changes their IDs and requires force-pushing the branch.

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/jessinra/lorekeeper/fix-pr-commit-titles
Any agent
npx skills add Jessinra/Lorekeeper --skill fix-pr-commit-titles
Clone the repo
git clone --depth 1 https://github.com/Jessinra/Lorekeeper

Made for: Claude Code, Codex.

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-pr-commit-titles

README.md
[![agentmods](https://agentmods.dev/badge/skills/jessinra/lorekeeper/fix-pr-commit-titles.svg)](https://agentmods.dev/skills/jessinra/lorekeeper/fix-pr-commit-titles)
Your own site
<a href="https://agentmods.dev/skills/jessinra/lorekeeper/fix-pr-commit-titles"><img src="https://agentmods.dev/badge/skills/jessinra/lorekeeper/fix-pr-commit-titles.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,008 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 $0.00038 $0.01008
Opus 5 $0.00019 $0.00504
Sonnet 5 $0.00008 $0.00202
Haiku 4.5 $0.00004 $0.00101

Measured 4d ago against content hash dc0b7a955a19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fix-pr-commit-titles 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 4d 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.

.hermes/skills/github/fix-pr-commit-titles/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix PR Commit Titles

Use when a PR has commits with the wrong title format (e.g. feat(lkpr-38): instead of [LKPR-38] feat:).


When to use

  • Commits on a PR branch don't match [LKPR-N] type: description
  • Interactive rebase (git rebase -i --reword) is impractical because the pre-commit hook fires on every commit and may abort on pre-existing lint violations

Approach: filter-branch --msg-filter

Rewrites all commit messages in a range in one pass. Does NOT trigger pre-commit or commit-msg hooks — avoids the hook-per-commit problem that breaks interactive rebase.

Trade-off: every SHA in the range changes, even commits whose messages weren't touched. Force-push to the PR branch is required.


Steps

1. Identify bad commits

cd ~/.hermes/profiles/diana/projects/lorekeeper

# Get PR head branch + commits
gh pr view <N> --json headRefName,commits \
  | python3 -c "import sys,json; d=json.load(sys.stdin); print('Branch:', d['headRefName']); [print(f\"{c['oid'][:8]} {c['messageHeadline']}\") for c in d['commits']]"

Or just inspect the local log:

git log --oneline -15

Look for commits with feat(lkpr-N):, fix(lkpr-N):, etc. instead of [LKPR-N] feat:.

2. Check out the PR branch

git checkout feat/lkpr-N-branch-name
# or, if not yet local:
git checkout -b feat/lkpr-N-branch-name origin/feat/lkpr-N-branch-name

3. Run filter-branch

Replace each wrong pattern with the correct [LKPR-N] type: form. The sed expressions are ANDed — each -e handles one pattern. Unmatched commits pass through unchanged.

FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch -f --msg-filter '
sed \
  -e "s/^feat(lkpr-38): /[LKPR-38] feat: /" \
  -e "s/^fix(lkpr-38): /[LKPR-38] fix: /" \
  -e "s/^chore(lkpr-38): /[LKPR-38] chore: /"
' <base-sha>..HEAD

<base-sha> is the last commit on main before the PR branch diverged. Get it with:

git merge-base HEAD origin/main

4. Verify

Read the full file on GitHub · 107 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. 4d ago First seen · 107 lines · 38 tokens per session scan A dc0b7a955a19

Subscribe to this mod's changes

fix-pr-commit-titles is a skill published in the GitHub repository Jessinra/Lorekeeper (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,008 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 2026-08-31.

Related

Other skills, from other repositories

commitlore-commits

Use when about to make a git commit and there is decision context worth recording — a constraint that shaped the change, an alternative that was tried and dropped, a warning for whoever touches this next. Drives the CommitLore capture pipeline, which drafts a record from the session transcript and the staged diff…

MongLong0214/commitlore · 235 tokens

commitlore-setup

Use when a git repository needs CommitLore wired up for the first time, or when its hook/notes configuration looks broken. Runs the diagnostic, installs the commit-msg validation hook, fixes the notes fetch refspec so records survive a clone or fetch, and builds the local record index. Trigger phrases include "set up…

MongLong0214/commitlore · 129 tokens

commitlore-commits

Capture a decision record from verified session and diff evidence before a commit.

MongLong0214/commitlore · 21 tokens

code-commit

Commit code changes with well-structured messages following Conventional Commits. Use when ready to commit after implementation or bug fix.

LuizEduPP/Rememb · 28 tokens

fresh-eyes-review

This skill should be used as a mandatory final sanity check before git commit, PR creation, or declaring work done. Triggers on "commit", "push", "PR", "pull request", "done", "finished", "complete", "ship", "deploy", "ready to merge". Catches security vulnerabilities, logic errors, and business rule bugs that slip…

2389-research/fresh-eyes-review · 83 tokens

Effective Memory

The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.

plur-ai/plur · 44 tokens