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-memo-referencegit clone --depth 1 https://github.com/mickeyyaya/evolve-loopWhat 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 | $0.00035 | $0.00799 |
| Opus 5 | $0.00017 | $0.00400 |
| Sonnet 5 | $0.00007 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
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.
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.mdfirst — come here only when you need the fullmemo.mdsection template or rationale. SeeCONTEXT.mdfor 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.
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.
- yesterday First seen · 53 lines · 35 tokens per session scan A 23de82f561ea
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.
Other agents, from other repositories
social-content-generator
Transform blog articles into platform-optimized social media content for all major platforms.
ai-antipatterns-reviewer
AI-code-antipatterns reviewer subagent. Auto-loads the ai-antipatterns skill; applies any .review-pro/ stack signals; returns structured findings.
spec-reviewer
Spec/intent reviewer subagent. Auto-loads the spec skill; applies any .review-pro/ stack signals; measures the diff against the resolved spec text; returns structured findings.
craft-reviewer
Craft (maintainability) reviewer subagent. Auto-loads the craft skill; applies any .review-pro/ stack signals; returns structured findings.
db-reviewer
Database & migration safety reviewer subagent. Auto-loads the db skill; applies any .review-pro/ stack signals; returns structured findings.
security-reviewer
Security reviewer subagent. Auto-loads the security skill; applies any .review-pro/ stack signals; returns structured findings.