Skip to main content
command CX Codex

triage — Claude Code command: what it does, how to install

triage evaluates security findings through a 7-question gate before you write a bug report. It helps bug bounty hunters discard invalid submissions immediately.

MIT ★ 16,193 updated 2026-10-29

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add elementalsouls/Claude-BugHunter
/plugin install claude-bughunter@elementalsouls
Open on GitHub

What triage does

The /triage command evaluates security findings using a rapid seven-question checklist before you write a report. It checks for an active HTTP request and verifies program scope. The first negative answer marks the finding as an immediate kill.

A fast kill checklist drops unchainable issues such as missing security headers or self-XSS. Unchained minor flaws get discarded. The command outputs one of three verdicts: GO to continue toward /validate, KILL with an explicit failure reason, or DOWNGRADE when proof of impact requires two accounts.

What it helps with

  • filter out theoretical vulnerabilities lacking an HTTP proof-of-concept
  • verify bug classification and program scope before reporting
  • discard non-submittable findings like missing headers and self-XSS
  • determine whether a low-impact bug qualifies as an exploit chain

Example prompts for the agent

  • /triage I can read other users' orders by changing user_id in /api/orders/{id}
  • /triage The /api/export endpoint returns 200 with data even with no auth header
  • /triage I found X-Forwarded-Host is reflected in the password reset email

How to install triage

1Plugin marketplace

/plugin marketplace add elementalsouls/Claude-BugHunter
/plugin install claude-bughunter@elementalsouls

2Manually: put the files in place

.claude/commands/triage.md

Call it with /triage. For all projects use ~/.claude/commands/

Questions about triage

How do I install triage in Claude Code?

Add the marketplace via /plugin marketplace add elementalsouls/Claude-BugHunter, then run /plugin install claude-bughunter@elementalsouls. You can also place the file in .claude/commands/triage.md.

What does the triage command do?

It runs a rapid 7-question gate to decide whether a bug bounty finding is ready to report or should be discarded. A single negative answer kills the submission on the spot.

How does triage differ from validate?

The /triage command is a fast go or no-go gate designed to save time. When all seven checks pass, the workflow proceeds to /validate for a thorough 4-gate verification before running /report.

Source text

triage.md · MIT
---
name: triage
description: Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage
---

# /triage

Quick triage to decide: submit or kill?

## When to Use

Use this before spending time writing a full report. If triage passes, run `/validate` for the full 4-gate check, then `/report`.

## Usage

```
/triage
```

Describe the finding in one sentence. Example:
- "I can read other users' orders by changing user_id in /api/orders/{id}"
- "The /api/export endpoint returns 200 with data even with no auth header"
- "I found X-Forwarded-Host is reflected in the password reset email"

## The 7 Questions (Fast Version)

Answer YES or NO to each. First NO = kill it immediately.

```
Q1: Can I demonstrate this with a real HTTP request RIGHT NOW?
    YES: I have the request/response already
    NO: I need to look at more code first → KILL

Q2: Is this impact type accepted by the program?
    YES: Bug class is on their accepted list
    NO: They explicitly exclude this type → KILL

Q3: Is the vulnerable asset owned by and in scope for the program?
    YES: Domain confirmed in-scope, not third-party
    NO: Third-party service or excluded domain → KILL

Q4: Does this work without admin/privileged access?
    YES: Regular user account is enough
    NO: Requires admin → KILL (99% of programs)

Q5: Is this NOT already known/disclosed/documented behavior?
    YES: Not in changelogs, not in disclosed reports
    NO: It's documented as intended → KILL

Q6: Can I prove impact beyond "technically possible"?
    YES: I have actual data in the response / action completed
    NO: I only have a 200 status or error message → DOWNGRADE

Q7: Is this NOT on the never-submit list?
    YES: It's a real bug class
    NO: Missing headers, self-XSS, open redirect alone, etc. → KILL or CHAIN
```

## Fast Kill Checklist

Kill immediately if ANY of these are true:
```
[ ] "Admin can do X" = not a bug
[ ] "Could theoretically lead to..." = no PoC = not a bug
[ ] Bug requires 3+ preconditions simultaneously
[ ] Finding is a missing header, missing flag, missing DMARC
[ ] SSRF with DNS callback only, no data returned
[ ] Open redirect with no OAuth chain or ATO path
[ ] Self-XSS (only affects your own account)
[ ] Introspection only (no IDOR, no auth bypass shown)
[ ] Rate limit on login/contact/search (Cloudflare covers it)
```

## Conditional Kill (chain required)

If it's on the never-submit list BUT you can chain it:
```
Open redirect → OAuth code theft → ATO        = report the chain
SSRF DNS → internal service access = data     = report the chain
CORS → credentialed data exfil PoC            = report the chain
Prompt injection → IDOR via chatbot           = report the chain
```

If you can't build the chain today → KILL IT.

## Output

**GO:** "All 7 pass. Run /validate for full check, then /report."

**KILL [reason]:**
- "Q1 fails — no HTTP request yet"
- "Q4 fails — requires admin access"
- "Q7 fails — open redirect alone is not submittable. Chain it with OAuth theft first."

**DOWNGRADE:**
- "Q6 — you have 200 status but not actual other-user data. Reproduce with two accounts and show victim's PII in the response before reporting."

© Sachin Sharma · MIT · elementalsouls/Claude-BugHunter

Similar slash commands

All slash commands for Security →

From the same set92

The whole set →
surface Shows a ranked attack surface for a target from its recon manifest and hunt memory. CX Codex +1 ★ 16,193repo stars intel Fetches target intelligence on demand: scans NVD and GitHub advisories, checks HackerOne reports, and flags untested endpoints from hunt memory. CX Codex +1 ★ 16,193repo stars scope scope is a Claude Code command that checks hosts and URLs before active testing. It blocks assets outside engagement rules during security work. CX Codex +1 ★ 16,193repo stars hunt-exceptional-conditions The hunt-exceptional-conditions skill reveals when an app leaks stack traces, server paths, or library versions through unhandled exceptions triggered by malformed input. Effective for testing APIs and web endpoints. CX Codex +1 ★ 16,193repo stars report Builds a submission-ready bug bounty report. Generates CVSS 3.1 score, proof of concept, impact statement, and fix in HackerOne, Bugcrowd, Intigriti, or Immunefi format. CX Codex +1 ★ 16,193repo stars validate validate — a validation command that culls weak findings before report writing. Runs a 7-Question Gate and 4-gate checklist to prevent submissions that damage your validity ratio. CX Codex +1 ★ 16,193repo stars autopilot autopilot is a Claude Code command for autonomous vulnerability hunting. It checks scope, ranks targets, validates findings, and drafts reports. CX Codex +1 ★ 16,193repo stars hunt-clickjacking hunt-clickjacking is a Claude Code skill that checks whether a page can be framed and used to trigger a sensitive action. It investigates clickjacking in web applications. CX Codex +1 ★ 16,193repo stars

Project sponsors

Companies that keep this analytics open