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.
npx agentmods add agents/mickeyyaya/evolve-loop/evolve-triage-referencegit clone --depth 1 https://github.com/mickeyyaya/evolve-loopWrote 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.
[](https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-triage-reference)<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-triage-reference"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-triage-reference.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01097 |
| Opus 5 | $0.00000 | $0.00549 |
| Sonnet 5 | $0.00000 | $0.00219 |
| Haiku 4.5 | $0.00000 | $0.00110 |
Grade A, and why
evolve-triage-reference 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Layer-3 reference — on-demand detail for the Triage agent. Read only when Triage Step 0 (inbox ingestion) needs algorithmic detail or when the Auditor needs schema verification. Routine cycles need not load this file.
TOC: Inbox JSON Schema · Ingestion Algorithm · Reconcile-Compatible Schema · Priority + Weight Scoring · Error Codes
Evolve Triage Reference — Inbox Ingestion (v9.5.0+)
Inbox JSON Schema
Files written by legacy/scripts/utility/inject-task.sh to .evolve/inbox/<ts>-<rand>.json:
| Field | Type | Required | Notes |
|---|---|---|---|
id |
string | yes | Unique; auto-generated as user-<epoch>-<hex8> if absent |
action |
string | yes | Non-empty task description |
priority |
enum | yes | HIGH | MEDIUM | LOW (stored uppercase) |
weight |
float|null | no | Tie-breaker within priority class; defaults to 0.5 if null |
evidence_pointer |
string | no | Auto-synthesized as inbox-injection://<injected_at> if absent |
operator_note |
string | no | Free-form operator context |
injected_at |
ISO8601 | auto | Set by inject-task.sh |
injected_by |
enum | auto | operator | test | automation |
Ingestion Algorithm
Step 0 in evolve-triage.md processes inbox files in this order:
- List
.evolve/inbox/*.json— maxdepth 1; skipprocessed/andrejected/subdirs. - Parse each file; malformed JSON → log
inbox-malformed-jsonWARN in## Inbox Errors, move to.evolve/inbox/rejected/cycle-<N>/, continue. - Validate required fields (
id,action,priority); missing/empty → WARN + reject. - Validate
priority∈ {HIGH, MEDIUM, LOW} andweight∈ [0.0, 1.0] or null; invalid → WARN + reject. - Check
iduniqueness againststate.json:carryoverTodos[]and already-ingested items; collision → WARN + reject. - Transform to reconcile-compatible schema (see below); append to working set.
- Move file to
processed/cycle-<N>/. - Write ledger entry:
role=triage, action=ingest-inbox, count=<ingested>, rejected=<rejected>.
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.
- today First seen · 82 lines · 0 tokens per session scan A eff750178edd
evolve-triage-reference is an agent published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,097 tokens. 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.
Other agents, from other repositories
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
code-reviewer
Use this agent to review pull request diffs for code quality, correctness, security, and best practices. Invoke when a PR is created and needs review before merge. Context: An issue PR has been created targeting the feature branch. assistant: "I'll use the code-reviewer agent to review this PR." Context: A feature PR…
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
company-finder
Discovery-mode agent. Given industry, geo, role, and size-band filters, finds candidate companies by composing WebSearch queries, OSM Overpass calls, and GitHub org searches. Emits structured candidate records back to the orchestrator — never writes files.
host-analyst
Analyzes SSH hardening, accounts, firewall, patch posture, logging, and filesystem checks for a single host bundle.
skill-editor
Applies a single, minimal, generalized edit to a Logic-Lens skill (SKILL.md / guide / shared file) given a concrete failure diagnosis. Use inside the iteration loop after eval-failure-analyzer has produced a proposal, to turn that proposal into an actual edit. Mutates files; does NOT run evals or sync the cache — it…