Checks for AI-assisted work
Evidence Harness
Check the project, permission and evidence behind an AI-assisted task. A portable skill supplies operating guidance; a small Python helper records whether the supplied facts allow the requested action.
From instruction to verification
A prompt is not an operating boundary
Before an agent changes anything, check that it has the right project and permission. Afterward, check the result. The skill explains the process; the Python helper evaluates the supplied evidence.
Route → authority → sense → bound → verify → receipt → improve
Operating guidance
- Decides whether a task needs the harness at all.
- Loads only the rules relevant to that task.
- Establishes which source is authoritative.
- Senses actual state before consequential action.
- Preserves explicit human authority.
- Asks for reproducible evidence before completion.
How it fits your workflow
- Use project tests and security reviews alongside the helper’s checks.
- Keep private prompts, customer information and operational records in your own environment.
- The project owner retains approval for deployment, publication and other external actions.
- Your project and hosting environment enforce access and execution permissions.
Public proof
The expected outcome is a refusal
The included fixture asks for a deployment while the observed project differs from the authoritative project and mutation authorization is absent. Evidence Harness records both reasons and executes no infrastructure command.
decision: blocked
reasons:
- mismatch:project
- authorization:missingThe helper evaluates the supplied files and writes a receipt. It does not execute a deployment or enforce an agent's network permissions.
Source and installation
Choose a release and run the example
The versioned GitHub release includes the skill, specification, receipt schema, synthetic fixture, four behavioral tests, public-hygiene scan, and complete release history.
Replay the example
Download and extract v0.1.0. From the extracted repository root, use Python 3—no model API key is needed:
python3 scripts/release_check.py
python3 skills/evidence-harness/scripts/harness_receipt.py \
--task examples/synthetic-infra-mismatch/task.json \
--authority examples/synthetic-infra-mismatch/authority.json \
--observed examples/synthetic-infra-mismatch/observed.json \
--output /tmp/evidence-harness-receipt.json