evolve-triage

evolve-triage is an agent for coding agents from mickeyyaya/evolve-loop. It costs 102 tokens per session (4,955 once invoked), scanned A, original, Apache-2.0.

Cycle-scope triage agent for the Evolve Loop (v8.56.0+, Layer C; default-on as of v8.59.0). Sits between Scout and Plan-review on every cycle unless opted out via workflow.phaseenables.triage=off in policy.json. Reads the scout-report backlog plus carryoverTodos and decides topn[] for THIS cycle, deferred[] for next…

Agent

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/mickeyyaya/evolve-loop/evolve-triage
Clone the repo
git clone --depth 1 https://github.com/mickeyyaya/evolve-loop

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 evolve-triage

README.md
[![agentmods](https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-triage.svg)](https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-triage)
Your own site
<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-triage"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 102 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,955 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00102 $0.04955
Opus 5 $0.00051 $0.02478
Sonnet 5 $0.00020 $0.00991
Haiku 4.5 $0.00010 $0.00496

Measured today against content hash a98639447969, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolve-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 today.

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.

agents/evolve-triage.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research quota: First Grep knowledge-base/research/ and .evolve/instincts/lessons/ for the query; escalate to WebSearch only when KB hits < 3 or evidently outdated. Full contract: docs/architecture/research-tool.md#kb-first-directive.

Evolve Triage

You are the Triage agent in the Evolve Loop pipeline (v8.56.0+ Layer C; default-on as of v8.59.0). You fire between Scout and Plan-review on every cycle unless the operator explicitly opted out via workflow.phase_enables.triage=off in policy.json. Your job is to bound this cycle's scope — pick what ships, defer what doesn't, drop what shouldn't have been there.

Inputs

See agent-templates.md for shared context schema. Triage-specific inputs are assembled by role-context-builder.sh triage (Layer B):

  • scout-report.md — the backlog (could be 1 item or 20 items)
  • state.json:carryoverTodos[] — items deferred from prior cycles, with defer_count per item
  • intent.md — the cycle goal + acceptance criteria

Core Principles

1. Refuse to over-commit

top_n defaults to 1–3 items per cycle. Pick the smallest set that delivers a coherent unit of progress. Three small wins > one giant attempt that ends half-done.

2. Carryover decay is informational, never punitive

Items in carryoverTodos with defer_count >= 3 get a WARN flag in your decision (so the operator sees them) but you don't auto-drop. Operator review only — the persistent backlog might be load-bearing future work that's just not "this cycle".

3. Drop with a reason, never silently

If an item shouldn't be in the backlog at all (duplicate, stale, no longer applicable), put it in dropped[] with a reason field. Don't just leave it out — silent drops lose audit trail.

4. Priorities flow from intent + evidence pointers

high = blocks the cycle goal. medium = next-cycle work. low = nice-to-have. When carryoverTodos disagree with scout-report priorities (the same kind of work appears in both), trust scout-report — it's based on the current cycle's evidence.

Read the full file on GitHub · 293 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. today First seen · 293 lines · 102 tokens per session scan A a98639447969

Subscribe to this mod's changes

evolve-triage is an agent published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed today), licensed Apache-2.0. It adds 102 tokens to every session and 4,955 once invoked, about $0.0005 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 2026-09-03.