agent-templates

Shared schemas and context rules that define the required fields and output structure for agents in an evolve-loop system.

In plain words
What is it for?
Use them when creating or updating agents that need a perspective, output format, model, capabilities, tools, and shared coordination context.
Why use it?
They prevent each agent definition from inventing its own format and keep information consistent when several agents work together.

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/agent-templates
Clone the repo
git clone --depth 1 https://github.com/mickeyyaya/evolve-loop
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,206 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 $0.00013 $0.04206
Opus 5 $0.00006 $0.02103
Sonnet 5 $0.00003 $0.00841
Haiku 4.5 $0.00001 $0.00421

Measured 2d ago against content hash 35c8a1c140a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-templates 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 2d 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.

agents/agent-templates.md · 328 lines

How it starts

The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Templates — Shared Schemas

v12.0.0 status: legacy/scripts/... paths referenced below were removed in the v12 flag day. Subagent dispatch, ledger writes, and team-context coordination are now in-process in the Go orchestrator + evolve subagent run CLI. Treat bash snippets as contracts; do not invoke them directly.

Shared input/output schemas for evolve-loop agents. Each agent references this file instead of duplicating boilerplate. Agent-specific fields are documented in the individual agent files.

Agent Definition Schema

Every agent file MUST include these frontmatter fields (in addition to name, description, model, capabilities, tools):

Field Type Required Description
perspective string yes The evaluative lens through which this agent interprets every input. Sets the default bias for all judgments. Example: "adversarial reviewer seeking failure modes".
output-format string yes Canonical structure of this agent's primary artifact — file name + section list. Enables deterministic merging in parallel fan-out scenarios. Example: "audit-report.md — Verdict, Defect Table, Eval Gate result".

Why these fields matter: In parallel builder fan-out (multiple specialist builders per cycle), the Orchestrator uses output-format to identify merge semantics automatically. The perspective field is injected verbatim into the agent's system prompt preamble, replacing fragile inline persona instructions.


Shared Context Block

All agents receive a JSON context block with these common fields:

Field Type Description
cycle number Current cycle number
workspacePath string Path to .evolve/workspace/
strategy string Evolution strategy: balanced, innovate, harden, repair, ultrathink
challengeToken string Per-cycle random hex token — embed in workspace output header and ledger entry
instinctSummary array Compact instinct array from state.json (inline)

Read the full file on GitHub · 328 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. 2d ago First seen · 328 lines · 13 tokens per session scan A 35c8a1c140a8

Subscribe to this mod's changes

agent-templates is an agent published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 13 tokens to every session and 4,206 once invoked, about $0.0001 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.