augint-tools
CLI orchestration layer for AI-assisted repository workflows.
Pipeline Artifacts
Reports are published to GitHub Pages on every push to the default branch.
| Report | Link |
|---|---|
| API Documentation | svange.github.io/augint-tools |
| Coverage Report | svange.github.io/augint-tools/coverage |
| Security Reports | svange.github.io/augint-tools/security |
| License Reports | svange.github.io/augint-tools/compliance |
| Test Report | svange.github.io/augint-tools/tests |
What This Does
augint-tools provides a stable, machine-parseable command surface for humans and AI agents to coordinate development workflows. It is designed to be called directly by AI skills, replacing ad-hoc shell scripts with reliable, JSON-enabled commands.
- AI-first design: Every command supports
--jsonoutput for agent parsing - Repo-type aware: Understands library and service repository patterns
- Safe defaults: No destructive git operations without explicit commands
- GitHub integration: Issue management, PR creation, CI status monitoring
- Health dashboard: Real-time TUI showing CI, PRs, issues, and compliance across all your repos
- YAML compliance engine: Declarative standards checking driven by a single
standards.yaml-- rule ownership lives with the standards maintainer, not in this tool
Getting Started
This project uses AI-assisted development. You do not need to memorize git commands or CI configuration -- your AI agent handles that.
Prerequisites
- Python 3.12+
- uv package manager
First-time setup
uv sync --all-extras
Running locally
# CLI help
uv run ai-tools --help
# Check repository status
uv run ai-tools repo status --json
# Run all pre-commit hooks
uv run pre-commit run --all-files
# Run tests
uv run pytest
Installation (from PyPI)
pip install augint-tools
Or with uv:
uv tool install augint-tools
How to Contribute
Contributions are made through AI agents (Claude Code, Copilot, etc.). You describe what you want changed in plain language; the agent handles branching, coding, testing, and submitting a pull request.
- Open Claude Code (or your AI agent) in this repo.
- Describe the change you want -- a bug fix, a new feature, a doc update.
- The agent will:
- Create a feature branch
- Make the changes
- Run pre-commit checks and tests
- Open a pull request
- Review the PR when the agent is done. CI runs automatically.
- Merge once CI is green.
If you need to work manually, see the full contributor guide (if available).
Architecture
Command Surface
ai-tools repo status # git state + upstream + open PR + CI + next action
ai-tools repo branch prepare # create work branch from correct base
ai-tools repo submit # run checks, push branch, create PR, enable automerge
ai-tools repo ci triage # classify CI failures
ai-tools repo check run # execute validation plan
ai-tools repo issues pick # issue recommendation and search
ai-tools dashboard --all # launch the compliance TUI
Global output flags: --json, --actionable, --summary
YAML Compliance Engine
The dashboard includes a declarative compliance engine that evaluates repos against rules defined in a standards.yaml file maintained in the ai-cc-tools repo. Rule ownership lives with the standards maintainer, not in augint-tools.
Adding a new compliance rule is a single YAML entry in ai-cc-tools -- no code change in augint-tools required (unless the rule needs a new handler type).
Built-in check types:
file_exists/file_absent-- verify presence of config filesfile_content_matches-- regex with numeric/string assertionsworkflow_job_has_step-- verify pipeline jobs contain required stepsworkflow_all_jobs_scan-- detect cheat patterns (|| true,continue-on-error,set +e)ruleset_has_required_checks-- verify GitHub rulesets enforce expected status checks
Handler escape hatch: For checks that need external data (AWS API calls, HTTP probes), a handler type dispatches to registered Python functions. Three built-in handlers: aws_oidc_trust_policy_scope, http_health_probe, and lambda_deploy_sha_match.
Dashboard Deployment Links
Each repo card can surface clickable shortcuts to its live deployment URLs (plus the repo's PyPI page for Python libraries). Links come from a user-global yaml file so the same config works from any terminal or WSL shell.
Yaml file
Path: ~/.augint/deployments.yaml (resolves to %USERPROFILE%\.augint\deployments.yaml on Windows).
Schema: a map of owner/repo slugs to a flat list of {label, url} entries.
augmentingintegrations/aillc-web:
- { label: dev, url: "https://www.org.aillc.link/" }
- { label: main, url: "https://www.augmentingintegrations.com/" }
augmentingintegrations/ai-lls-api:
- { label: dev, url: "https://lls-api.lls.aillc.link" }
- { label: main, url: "https://lls-api.landlinescrubber.link" }
Reserved labels
| label | glyph | treatment |
|---|---|---|
main |
p |
prod -- middle-click on card title opens this |
dev |
s |
staging -- shift + middle-click on card title opens this |
pypi |
π |
auto-synthesized for Python libraries; manual entry overrides |
Interaction model
Keyboard shortcuts (work on the selected repo, one-hand cluster):
| Key | Action |
|---|---|
z |
Open prod/main deployment URL |
x |
Open dev/staging deployment URL |
c |
Open 1st supplemental link (after main/dev) |
v |
Open 2nd supplemental link |
b |
Open 3rd supplemental link |
f |
Open the "Manage deployment links" modal |
Mouse (on the title row):
- Middle-click on the title -> open prod URL (falls back to GitHub repo page if no
mainlink) - Shift + middle-click on the title -> open dev URL
- Ctrl + left-click on the title -> open the "Manage deployment links" modal
- Left-click on a glyph -> terminal-native OSC-8 link opens the URL directly
The detail drawer (press d) lists every link in a deployments: section with the host shown as visible text and the full URL as the OSC-8 target.
Manage modal
Press f or middle-click on the repo name to open a modal scoped to the selected repo. The modal has dedicated fields for Production and Staging URLs at the top (Set/Clear), plus an add row for supplemental links. Existing supplementals are listed inline with Remove buttons. Every mutation writes the yaml immediately.
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for augint-tools 5.42.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| augint_tools-5.42.5.tar.gz | 202.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| augint_tools-5.42.5-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 465.4 kB
Release files / augint_tools-5.42.5.tar.gz
| Download URL | augint_tools-5.42.5.tar.gz |
|---|---|
| Size | 202.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4601759ed518df7a256de20792f6bd4800191e9a1074a94a08fe7c7603a446e2
|
|
BLAKE2b-256 checksum How to use checksums |
c921cbcf96722dedea44b973d1b0dcd3c7fb0e23b14f6a9ba3bd74f3d150b9bf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.13
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 1, 2026.
Transparency logRelease files / augint_tools-5.42.5-py3-none-any.whl
| Download URL | augint_tools-5.42.5-py3-none-any.whl |
|---|---|
| Size | 262.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
da4f9858ef18de7487bcabc4d43416913653e30a236ef0e14a89d34604766bc0
|
|
BLAKE2b-256 checksum How to use checksums |
907f4dfc0c1dc98885716748d837cfc99ffdffdbcbc3fbb80ba9689acfaddd20
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.13
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 1, 2026.
Transparency log
