A command for opening a GitHub pull request from a feature branch to the hotfix branch, including a summary of the release changes.

Use it when implementation is complete and committed, to push the feature branch, review its commits and changes, and create the pull request.

It standardizes the final review step and checks that the work is committed, on the right branch, and ready to push. A pull request is a request for others to review and merge code changes.

create-pr — Command by cognitx-leyton

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 commands/cognitx-leyton/codegraph/create-pr

Clone the repo

git clone --depth 1 https://github.com/cognitx-leyton/codegraph

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 713 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5	$0.00013	$0.00713
Opus 5	$0.00006	$0.00357
Sonnet 5	$0.00003	$0.00143
Haiku 4.5	$0.00001	$0.00071

Measured 2d ago against content hash 25607f2d8ab5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

create-pr scanned grade C 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 2d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

PYPI_VERSION=$(curl -s https://pypi.org/pypi/cognitx-codegraph/json 2>/dev/null | python3 -c "import sys,json; print(json.load(sys.stdin)['info']['version'])" 2>/dev/null || echo "not published")

Makes network callslowCapability

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

allowed-tools: Bash(git:*), Bash(gh:*), Bash(grep:*), Bash(curl:*)

.claude/commands/create-pr.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create PR (Step 12 — final workflow step)

Create a pull request from the current feature branch to hotfix with a full description of what was implemented.

Process

1. Verify state

git branch --show-current   # must be a feature branch (feat/, fix/, chore/)
git status -s               # should be clean
git log --oneline hotfix..HEAD # commits to include

If uncommitted changes exist: STOP, run /commit first. If on a protected branch (main/release/hotfix): STOP, wrong branch.

2. Push the feature branch

BRANCH=$(git branch --show-current)
git push origin "$BRANCH"

3. Get PyPI version (if packaged)

PYPI_VERSION=$(curl -s https://pypi.org/pypi/cognitx-codegraph/json 2>/dev/null | python3 -c "import sys,json; print(json.load(sys.stdin)['info']['version'])" 2>/dev/null || echo "not published")

4. Analyze commits

Review ALL commits between hotfix and the feature branch:

BRANCH=$(git branch --show-current)
git log --oneline hotfix.."$BRANCH"
git diff --stat hotfix.."$BRANCH"

Identify: type of change (feat/fix/refactor), scope, key changes.

5. Comment on the source issue (if applicable)

If an issue number was mentioned, add an implementation summary:

gh issue comment <N> --body "## Implementation Complete
**Package:** cognitx-codegraph=={version}
### What was done
- <summary>
### Tests
- {N} tests passing
This issue will be automatically closed when the PR is merged."

6. Create PR

Include Closes #N in the body so GitHub auto-closes the issue on merge. Do NOT manually close the issue.

BRANCH=$(git branch --show-current)
gh pr create --base hotfix --head "$BRANCH" --title "<type>: <concise description>" --body "$(cat <<'EOF'
Closes #<N>

## Summary
- <bullet 1: what changed>
- <bullet 2: what changed>

## Test plan
- [x] Unit tests: {N} passed
- [x] Byte-compile clean
- [x] Code review: clean
- [x] Critique: PASS
- [x] Self-index verified
- [ ] Leytongo real-world test

## Package
PyPI: `cognitx-codegraph=={version}`
Install: `pip install cognitx-codegraph=={version}`

Generated with [Claude Code](https://claude.com/claude-code)
EOF
)"

Read the full file on GitHub · 105 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.

2d ago First seen · 105 lines · 13 tokens per session scan C 25607f2d8ab5

Subscribe to this mod's changes

create-pr is a command published in the GitHub repository cognitx-leyton/codegraph (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 713 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code review Git and workflow Research ast code-analysis codebase-search cypher dependency-graph graphrag

create-pr