promptguard
Enrichment pendingAudits prompts as behavioral contracts. Pre-write guard for agents that ship code.
GraphCanon updated today · GitHub synced today
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Steady (59d since push)
- As of today
- Provenance
- Not a fork · Personal account
- As of today
- Security (OSV)
- No lockfile
- As of today
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install promptguardSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Audits prompts as behavioral contracts. Pre-write guard for agents that ship code.
Capability facts
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Jul 15, 2026
- Languages
- python
Source: github.language+pyproject.toml · Jul 15, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Jul 15, 2026)
python3 -m promptguard audit prompts.pySource link
Tags
README
Quick Start
Run without installing:
python3 -m promptguard audit prompts.py
printf '%s' 'Fix this bug and write code.' | python3 -m promptguard audit - --format markdown
Install as a local CLI:
python3 -m venv .venv
source .venv/bin/activate
python -m pip install -e .
promptguard audit prompts.py
Install as an app with pipx:
pipx install promptguard
promptguard audit prompts.py
Install from GitHub before a package release:
pipx install "git+https://github.com/<owner>/promptguard.git"
Save reports:
promptguard audit prompts.py --format json --save
Saved reports go to:
.promptguard/reports.jsonl
For agents
This page has a .md twin and JSON over the API.