beneissue

Drowning in GitHub issues? Install beneissue once, and it handles the rest automatically.

Who is this for?

Open source maintainers with 100+ issues piling up
Small teams who can't afford to manually label every issue
Solo developers who want typo fixes handled automatically

What changes after you install it?

Before	After
Issue opened → check it days later	Issue opened → instantly classified + labeled
Manually comment "need more info"	Auto-asks specific follow-up questions
Fix simple bugs yourself	Auto-eligible issues get auto-PR via Claude Code

Install once, runs forever

1. Install the package

pip install beneissue

2. Set up GitHub repository secrets

Go to your repo → Settings → Secrets and variables → Actions, and add:

Secret	Required	Description
`ANTHROPIC_API_KEY`	Yes	Your Claude API key
`LANGCHAIN_API_KEY`	No	LangSmith for tracing

3. Initialize in your repo

cd your-repo
beneissue init
git add .github/ .claude/
git commit -m "Add beneissue automation"
git push

That's it. From now on:

New issue opened → automatically triaged and labeled
Auto-eligible issues → Claude Code creates a PR
Need manual control? → just comment on the issue

Control via issue comments

@beneissue triage    # Re-classify this issue
@beneissue analyze   # Run full analysis
@beneissue fix       # Attempt auto-fix now

No CLI needed. Just talk to the bot in the issue thread.

How it works

Issue opened
    ↓
[Triage] → valid / invalid / duplicate / needs-info
    ↓
[Analyze] → affected files, fix approach, checklist
    ↓
[Fix] → auto-eligible? → Claude Code creates PR

Verify it's working

When issues get these labels automatically, you're set:

triage/valid — Valid issue, ready for work
fix/auto-eligible — Will be auto-fixed

Configuration

Edit .claude/skills/beneissue/beneissue-config.yml:

version: "1.0"

models:
  triage: claude-haiku-4-5    # Fast, cheap (~$0.02/call)

limits:
  daily:
    triage: 50   # ~$1/day
    analyze: 20  # ~$2-10/day
    fix: 5       # ~$5-25/day

team:
  - github_id: "your-github-id"
    available: true
    specialties: ["backend", "python"]

observability:
  langsmith:
    enabled: true
    project: "beneissue"

Labels

Label	Meaning
`triage/valid`	Valid issue, ready for analysis
`triage/invalid`	Out of scope or spam
`triage/duplicate`	Already reported
`triage/needs-info`	Waiting for more details
`fix/auto-eligible`	Passes checklist, will be auto-fixed
`fix/manual-required`	Needs human review
`fix/completed`	Auto-fix PR created

CLI (optional)

For manual runs or debugging:

Command	Description
`beneissue triage <repo> --issue <n>`	Classify issue only
`beneissue analyze <repo> --issue <n>`	Analyze issue only (no triage, no fix)
`beneissue fix <repo> --issue <n>`	Fix issue only (no triage, no analysis)
`beneissue run <repo> --issue <n>`	Full workflow: triage → analyze → fix
`beneissue init`	Initialize beneissue in current repo
`beneissue labels`	Sync labels to repository
`beneissue test`	Run policy tests

Add --dry-run to triage/analyze to skip GitHub actions.

License

Apache 2.0

Metadata

Release files for beneissue 1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for beneissue 1
File	Size	Uploaded
beneissue-1.tar.gz	20.8 kB	Dec 25, 2025	Details

Built distribution (wheel)

Table of built distributions (wheels) for beneissue 1
File	Interpreter	ABI	Platform	Reset
beneissue-1-py3-none-any.whl 30.4 kB Dec 25, 2025	Python 3	none	any	Details

Total release size: 51.2 kB

Release files / beneissue-1.tar.gz

Download URL	beneissue-1.tar.gz
Size	20.8 kB
Tags	Source
SHA-256 checksum How to use checksums	`0008f6e244cc44ec9cc14241af4797e8897da0f3262a006da6e12dbd77460cde`
BLAKE2b-256 checksum How to use checksums	`635788d4a265067e10daab83003e42572c8f61429f385ee92c329887fe1cab2b`
Upload date	Dec 25, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.7`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/opendataloader-project/beneissue
Publishing commit: github.com/opendataloader-project/beneissue/tree/e3ad0fb1a201883494bcb4ffe7bffe177d3e5c0c

Workflow

Publishing configuration: github.com/opendataloader-project/beneissue/blob/e3ad0fb1a201883494bcb4ffe7bffe177d3e5c0c/.github/workflows/publish.yml
Publishing logs: github.com/opendataloader-project/beneissue/actions/runs/20497493558/attempts/1

Artifact

Subject: beneissue-1.tar.gz
SHA-256 checksum: 0008f6e244cc44ec9cc14241af4797e8897da0f3262a006da6e12dbd77460cde Verifying attestations

Release files / beneissue-1-py3-none-any.whl

Download URL	beneissue-1-py3-none-any.whl
Size	30.4 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`de140a5f07a95aa92901f17d064329dde8de2ccbda77c6063225a4913a2cb9f3`
BLAKE2b-256 checksum How to use checksums	`006f9ce3f21b50d406236ce0c8ff8c46bb0c795a13959399e61a4a348c2d5334`
Upload date	Dec 25, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.7`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/opendataloader-project/beneissue
Publishing commit: github.com/opendataloader-project/beneissue/tree/e3ad0fb1a201883494bcb4ffe7bffe177d3e5c0c

Workflow

Publishing configuration: github.com/opendataloader-project/beneissue/blob/e3ad0fb1a201883494bcb4ffe7bffe177d3e5c0c/.github/workflows/publish.yml
Publishing logs: github.com/opendataloader-project/beneissue/actions/runs/20497493558/attempts/1

Artifact

Subject: beneissue-1-py3-none-any.whl
SHA-256 checksum: de140a5f07a95aa92901f17d064329dde8de2ccbda77c6063225a4913a2cb9f3 Verifying attestations