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-reflector-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-reflector-reference)<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-reflector-reference"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-reflector-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 | $0.00280 |
| Opus 5 | $0.00000 | $0.00140 |
| Sonnet 5 | $0.00000 | $0.00056 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
evolve-reflector-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.
What it actually says
Layer-3 reference — on-demand detail for the Reflector agent. Read only when historical context about the reflector's origin is needed. Routine cycles need not load this file.
Evolve Reflector Reference
This file holds the historical narrative for the Reflector phase agent.
The operational workflow (Inputs, Workflow, Ledger Entry, What NOT to do) lives in agents/evolve-reflector.md.
Why this agent exists
Before v10.20.0, the per-phase friction signal was scattered: Builder's Known Gap section, Scout's Risk Assessment, Auditor's Defects — all named different things, lived in different reports. Retrospective dug them out only on FAIL/WARN, so PASS cycles dropped the signal. The reflector closes that gap by:
- Standardizing per-phase friction into a single schema (
<phase>-reflection.yaml). - Aggregating across cycles so systemic patterns surface mechanically ("research-quota 4/5 cycles" rather than "Builder complained again, did I see this last week?").
- Producing one operator-facing synthesis per cycle, regardless of verdict.
You are the "always-on" half of the Learn phase. Retrospective and memo are the verdict-conditional halves that consume your synthesis. Together: every cycle ends with a clean picture of per-phase improvement and pipeline-level health.
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 · 17 lines · 0 tokens per session scan A 1c50446b3ebd
evolve-reflector-reference is an agent published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 280 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
design-sync
Detects conflicts across multiple Design Docs and provides structured reports. Use when multiple Design Docs exist, or when "consistency/conflict/sync/between documents" is mentioned. Focuses on detection and reporting only, no modifications.
document-reviewer
Reviews one document or one ADR batch against governing requirements, repository evidence, and the needs of its next consumer. Use before user approval or when document consistency and completeness need verification.
code-verifier
Verifies repository-backed claims and implementation feasibility in PRDs, Design Docs, or Work Plans. Use before document review, after implementation, or for reverse-engineered artifact verification.
data-engineer
Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…
technical-designer
Creates a scoped ADR batch or one backend/general Design Doc from confirmed requirements and decision-relevant repository evidence. Use when technical choices or implementation design need an approved artifact.
prd-creator
Creates PRD and structures business requirements. Use when new feature/project starts, or when "PRD/requirements definition/user story/what to build" is mentioned. Defines user value and success metrics.