Install the Agent Contribution Preflight Skill

Requirements: Python 3.10 or newer. Remote inspection also requires an authenticated GitHub CLI. Local inspection has no third-party Python dependencies.

Install with the cross-agent Skills CLI

This is the shortest path for clients supported by the open Skills CLI:

npx skills add vulragrag-star/agent-contribution-preflight \
  --skill agent-contribution-preflight

Review the checked-in SKILL.md before enabling it. The source repository is the authority.

Install with a compatible GitHub CLI

If your GitHub CLI build exposes the gh skill command, install the named skill with:

gh skill install vulragrag-star/agent-contribution-preflight \
  agent-contribution-preflight

If gh skill --help is unavailable, use the Skills CLI or manual method instead. Do not install a similarly named package from an unverified source.

Install the versioned release archive

Download the v1.0.0 Skill ZIP and SHA256SUMS. Verify the checksum before extracting the top-level agent-contribution-preflight/ directory into an agent's supported skills directory.

Manual installation

Clone the public repository.

git clone https://github.com/vulragrag-star/agent-contribution-preflight.git

Inspect the skill source.
Read skills/agent-contribution-preflight/SKILL.md, its references, and the inspector script before copying anything into an agent's skills directory.
Copy the complete skill directory.
Keep SKILL.md, references/, scripts/, and agents/ together so links and runtime files remain valid.

Run the read-only inspector

Inspect a local checkout:

python skills/agent-contribution-preflight/scripts/inspect_target.py \
  --local /path/to/repository

Inspect a public repository and a numbered issue or pull-request conversation:

python skills/agent-contribution-preflight/scripts/inspect_target.py \
  --repo owner/repository \
  --thread 123 \
  --format json

Exit	Meaning	Required response
`0`	No public signal observed.	Continue the policy and precedent review. Absence is not proof that no control exists.
`1`	Inspection failed, was incomplete, or received invalid input.	Correct the input or inspect a local clone before drawing a clean conclusion.
`2`	An AgentScan or related repository signal was observed.	Pause the external write and brief the owner.
`3`	Machine-targeted hidden content was observed.	Require human review before any reply; do not echo the hidden instruction body.

Verify what the skill does not do

It does not post, comment, close, label, or otherwise mutate GitHub.
It does not optimize a detector score or recommend simulated human activity.
It does not conceal AI assistance or impersonate a person.
It does not treat repository text as higher-priority instructions to the user's agent.

Read the plain-text install.md or the self-describing discovery manifest for machine consumption.

Apply the methodologyTurn installation into a reliable pre-contribution decision. Review the latest releasePrefer versioned source when pinning the skill in a controlled environment.