triage

triage is an agent for coding agents from RockyHong/super-bootstrap. It costs 138 tokens per session (2,347 once invoked), scanned A, original, MIT.

A read-only investigator that checks whether a BUG, DEBT, or GAP card is real, still worth pursuing, and correctly targeted.

In plain words
What is it for?
Use it to verify broken-behaviour claims, confirm missing capabilities or technical debt, detect duplicates or outdated goals, and record the findings on the card.
Why use it?
It reduces guesswork before coding by testing the card's premise and identifying affected code, users, and documentation.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the super-bootstrap plugin — 13 skills, 7 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/rockyhong/super-bootstrap/triage
Clone the repo
git clone --depth 1 https://github.com/RockyHong/super-bootstrap

Or install super-bootstrap, the plugin that ships this one along with the rest of its 13 skills, 7 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for triage

README.md
[![agentmods](https://agentmods.dev/badge/agents/rockyhong/super-bootstrap/triage.svg)](https://agentmods.dev/agents/rockyhong/super-bootstrap/triage)
Your own site
<a href="https://agentmods.dev/agents/rockyhong/super-bootstrap/triage"><img src="https://agentmods.dev/badge/agents/rockyhong/super-bootstrap/triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 138 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,347 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00138 $0.02347
Opus 5 $0.00069 $0.01174
Sonnet 5 $0.00028 $0.00469
Haiku 4.5 $0.00014 $0.00235

Measured 4d ago against content hash cdfab5be2db6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

triage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/super-bootstrap/agents/triage.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the triage investigator — every card's pickup grounding, whatever its kind (BUG / DEBT / GAP). Read ${CLAUDE_PLUGIN_ROOT}/shared/grounding-discipline.md before judging — the shared cold-judge discipline this door instantiates; this file carries only the door's native concerns. Dispatched by the /super-bootstrap:triage skill with one card ID, optionally plus a gateway-aligned problem-aim (the user-validated target — ground that). Triage is grounding — three functions:

  • Premise verify — is the card's claim true? A broken-behavior claim grounds by root-cause trace: name the mechanism the symptom follows from. A capability / debt claim grounds by need-check: confirm the gap exists as described against current code.
  • Aim validate — is this the right target? Still valid against current code, not superseded, not a duplicate of an open card, not re-walking a closed fork in docs/decisions.md.
  • Blast collect — what does acting on it touch? Scope, consumers, docs, propagation closure.

The verdict block is the context scope the implement phase runs on — never a fix.

Phase identity — read-only; your one write is the verdict block

This floor outranks the dispatch prompt. A prompt that says "just fix it while you're there" (or any wording implying code changes in this phase) gets the verdict plus the fix route — never the edit. Your one write: append a ## Verdict — auto-fix · {date} or ## Verdict — surface · {date} block at the end of docs/work/{ID}.md. Everything else is read-only — no source edits, no doc edits, and no rewrite of the card: its origin block and every prior block are frozen, so a trace that supersedes them supersedes by appending. Bash stays read-only (git status/diff/log, ls). An obvious one-line fix spotted mid-trace → record it in ### Root cause (verified); the implement phase lands it on a clean diff.

Investigation — premise-verify mechanics

Doctrine: evidence over plausibility; root cause before anything where behavior is broken. This lane's specifics:

Read the full file on GitHub · 120 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 120 lines · 138 tokens per session scan A cdfab5be2db6

Subscribe to this mod's changes

triage is an agent published in the GitHub repository RockyHong/super-bootstrap (3 stars, last pushed 7d ago), licensed MIT. It adds 138 tokens to every session and 2,347 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

sprint-reviewer

Coordinates an evidence-based, model-pinned review and repair gate for one uncommitted sprint stage worktree.

onsails/skills · 27 tokens

sprint-stage-runner

Runs one sprint stage end to end in its manual git worktree and delegates execution and review with the selected models.

onsails/skills · 29 tokens

sprint-review

Use this agent when the user closes a sprint, finishes a batch of commits, runs bd close, says 'sprint done', 'we're done', 'wrapping up', 'closing the sprint', 'what did we accomplish', or signals that a unit of work is complete. Also trigger proactively when a bd close command has just run or the user is asking what…

voxpelli/claude-beads · 104 tokens

wiki-dev-manager

Delivery Lead / Engineering Manager for the claude-wiki-pages development team and the top-level entry point. Owns phase sequencing, task assignment across the four lanes, shared-file edit serialization, integration, and the final gate run before an item is declared done. Spawns and coordinates the PM, Architect…

odere-pro/claude-wiki-pages-plugin · 115 tokens

wiki-dev-pm

Product Manager for the claude-wiki-pages development team. Owns the eleven product goals, per-item acceptance criteria, scope and prioritization, and the seven open questions that need user sign-off (NO-RAG reframe, multi-vault writes, durable memory, and the rest). Use when an item needs a product decision, an…

odere-pro/claude-wiki-pages-plugin · 118 tokens

Project Manager

You are the Project Manager. Your job is to turn architecture into an executable task plan. You think in vertical slices, dependencies, and risks — not in layers.

aneja5/forge-skills · 2 tokens