evolve-memo-reference

A reference for producing a short cycle memo in the Evolve Loop, a repeated process for improving a project. It defines the memo’s required sections and the information the next cycle needs.

In plain words
What is it for?
It guides the artifact index, skill suggestions, carryover priorities, sequencing rationale, and required cycle-summary format.
Why use it?
It prevents memo outputs from being mistaken for audit reports and ensures later planning has a consistent summary of shipped work and follow-up tasks.

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-memo-reference
Clone the repo
git clone --depth 1 https://github.com/mickeyyaya/evolve-loop
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 799 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 $0.00035 $0.00799
Opus 5 $0.00017 $0.00400
Sonnet 5 $0.00007 $0.00160
Haiku 4.5 $0.00003 $0.00080

Measured yesterday against content hash 23de82f561ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolve-memo-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 yesterday.

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-memo-reference.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evolve Memo Reference

Layer-3 on-demand reference for the Layer-P memo phase. Read the Layer-P Memo Phase Contract section in agents/evolve-orchestrator.md first — come here only when you need the full memo.md section template or rationale. See CONTEXT.md for canonical definitions of "memo", "cycle memo", and "Layer-P".

memo-template

memo.md is a cycle memo, not a report. Its audience is the next cycle's orchestrator and Scout, not an auditor reviewing the current cycle. Every section listed below is required; the total document MUST be ≤100 lines.

Required sections (in order)

Section heading Content rule
## Cycle N — Memo State the cycle number and one sentence summarizing what shipped
## Artifact Index List each cycle report by relative path and SHA8; do NOT paraphrase or excerpt content
## Skill Suggestions List 2–4 persona-action suggestions for the next cycle, each naming a specific carryover ID and the recommended evolve-loop flag or persona mode
## carryoverTodo Guidance Name which carryover IDs to prioritize next cycle, state the sequencing rationale, and note any preconditions satisfied this cycle

Artifact Index format

Each entry in ## Artifact Index is a single prose line stating the relative path (from $PROJECT_ROOT) and the SHA8 of the file at the time of ship. The orchestrator MUST NOT quote, excerpt, or paraphrase content from these files — the index is a pointer, not a summary. Path and SHA8 are sufficient for the next cycle's agents to locate and read the artifact independently.

Skill Suggestions format

Each suggestion is one imperative sentence naming the carryover ID it targets, the recommended persona or configuration, and optionally why. Two to four entries. Suggestions map directly to evolve-loop persona actions: a subagent-run.sh invocation variant or an env flag to enable. Keep each suggestion to one sentence.

carryoverTodo Guidance format

State the top-pick ID and its sequencing rationale in 2–4 sentences. If a precondition was satisfied this cycle (for example, c27 shipped and unblocks c28 and c29), say so explicitly so the next orchestrator does not need to re-derive it from the full carryover list.

Read the full file on GitHub · 53 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. yesterday First seen · 53 lines · 35 tokens per session scan A 23de82f561ea

Subscribe to this mod's changes

evolve-memo-reference is an agent published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 799 once invoked, about $0.0002 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.