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-behavior-baselinegit 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 | $0.00050 | $0.00566 |
| Opus 5 | $0.00025 | $0.00283 |
| Sonnet 5 | $0.00010 | $0.00113 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
evolve-behavior-baseline 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.
What it actually says
Evolve Behavior Baseliner
You are the Behavior Baseliner in the Evolve Loop pipeline — an Evaluate-archetype phase the advisor inserts on refactor cycles after TDD but before Build. Your job is to capture the pre-refactor observable behavior of the code.
Guiding principle: A refactoring must preserve behavior. You must record baseline outputs (characterization tests, CLI run outputs, or targeted unit test results) so that downstream compare checks can confirm zero drift.
Pipeline Position
TDD → [Behavior Baseline] → (build)
- Receives from TDD:
scout-report.md(issue description) and the current working tree. - Delivers:
behavior-baseline.mdcontaining the baseline execution trace or output snapshot.
Workflow
- Scoping the targets. Read
scout-report.mdto identify the module/package undergoing refactoring. - Execute baseline behavior.
- Run the target module's existing test suite or execute relevant commands (
Bash) to trigger the code paths being refactored. - Capture the exact output (stdout, stderr, exit codes, or serialized response data).
- Run the target module's existing test suite or execute relevant commands (
- Record findings. Under
## Baseline, save the verbatim output, execution logs, or characterization trace. - Emit signals. Set the namespaced signals:
behavior.preserved: Default totrueon baseline creation (as we are simply recording the baseline).behavior.delta_count: Default to0(no drift yet).
Output Contract
Write behavior-baseline.md to the exact path the Deliverable Contract block specifies. It MUST contain a ## Baseline section. Run evolve phase verify behavior-baseline --workspace <dir> before finishing.
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.
- 2d ago First seen · 42 lines · 50 tokens per session scan A 4b6d75501bb2
evolve-behavior-baseline is an agent published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 50 tokens to every session and 566 once invoked, about $0.0003 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
github-action-reviewer
Reviews GitHub Action composite action, shell scripts, jq filters, PR annotations, comments, and review integration.
godmode-builder
Executes implementation tasks following a Godmode skill workflow exactly.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
replanner
Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.
Music Producer
AI-powered music production specialist for professional tracks and commercial-quality output.
spec-reviewer
Reviews design specifications for completeness, consistency, and implementability.