Triage Ranker — Development agent for Claude Code
Severity ranker for one confirmed triage finding.
How to install Triage Ranker
Installs to ~/.claude/agents/air-gapped-skills-triage-ranker.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/air-gapped/skills/HEAD/.claude/agents/triage-ranker.md -o ~/.claude/agents/air-gapped-skills-triage-ranker.md Restart Claude Code, or start a new session, for it to be picked up.
What Triage Ranker does
name: triage-ranker description: Severity ranker for one confirmed triage finding. Spawn with a repo path, deployment context, and finding fields — not for general delegation. tools: Read, Glob, Grep
You are assigning severity to a CONFIRMED security finding. Verification already happened; assume the finding is real (reachable as described). Your only job is to derive how bad it is, independently of what the scanner claimed. Severity is IMPACT x EXPLOITABILITY: what the attacker actuall
Alternatives in Development
- Recon Ranker — Attack surface ranking agent 4.5k ★
- Dast Devils Advocate — Adversarial validator for DAST findings 812 ★
- Platform Ranker — 플랫폼 랭킹·연재 구조 조사 전문가 305 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Triage Verifier
Adversarial verifier for one scanner finding in a triage run. Spawn with a repo path, environment, and finding
Patch Author
Patch author for one verified vulnerability finding in a patch run. Spawn with a repo path and a nonce-tagged
Codex Triage
Feature-workflow review triage. Reads one round's finished /codex challenge output file(s) — all slices of a s
Refute Verifier
Clean-context skeptic that tries to REFUTE each draft finding or claim it is given — verdicts CONFIRMED / REFU
Mr Reviewer
Fresh-context, read-only review of one merge request against the problem it claims to solve: fit, extra, the d
Phase Implementer
Invoked by /orchestrate to implement one plan phase end-to-end — read the phase block, write the code, run tar
Related Skills
POC
Generate an executable proof-of-concept exploit for a confirmed High/Critical finding — detect the toolchain,
Bounty
Generate a responsible-disclosure bounty submission from a confirmed finding — Immunefi / protocol bounty / SE
Audit Crds
Audit CRDs and controllers for inconsistencies, dead fields, and unimplemented features — then file GitHub iss