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/reflection-authoring-stepgit 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/reflection-authoring-step)<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/reflection-authoring-step"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/reflection-authoring-step.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 | $0.00035 | $0.01358 |
| Opus 5 | $0.00017 | $0.00679 |
| Sonnet 5 | $0.00007 | $0.00272 |
| Haiku 4.5 | $0.00003 | $0.00136 |
Grade A, and why
reflection-authoring-step 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 today.
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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reflection Authoring Step
v12.0.0 status:
legacy/scripts/...paths referenced below were removed in the v12 flag day. Reflection sidecar writes and aggregation are owned by the Go reflection package (go/internal/reflection/). Treat bash snippets as contracts; do not invoke them directly.Referenced verbatim by all 9 phase agent personas (Intent, Scout, Triage, Plan-Review, Build-Planner, TDD-Engineer, Tester, Builder, Auditor). Gated on
EVOLVE_REFLECTION_JOURNAL(default1at v10.20.0;0opts out). Schema details: agents/agent-templates.md → Reflection Journal Schema.
Purpose
Every phase agent surfaces a bounded reflection on its own execution so the Learn phase can aggregate per-phase friction and cross-cycle patterns. This is process retrospection, not code-quality review (distinct from the self-review loop).
Workflow (3 steps, before posting your completion ledger entry)
-
Read your phase-tracker metrics from
.evolve/runs/cycle-<N>/.ephemeral/metrics/<phase>.json(already produced bylegacy/scripts/observability/rollup-cycle-metrics.sh). Extractlatency_ms,cost_usd,turns— these populate your reflection'sphase_tracker_refsblock. Do NOT recompute these numbers. -
Write
$WORKSPACE/<phase>-reflection.yamlfollowing the YAML schema in agent-templates.md → Reflection Journal Schema. Required keys:schema_version: 1,cycle,phase,agent,phase_smooth,suggested_improvements[](≥1),reflection_confidence(0.0-1.0),phase_tracker_refs{}. Optional:slowdowns[],friction_received_from[],blind_spots[]. Keep the file ≤30 lines. -
Append the
## Reflectionmarkdown section to your primary report (<phase>-report.mdor equivalent — e.g.,intent.md,scout-report.md,triage-report.md,plan-review.md,build-plan.md,test-report.md,tester-report.md,build-report.md,audit-report.md). Bracket the section with<!-- BEGIN reflection -->/<!-- END reflection -->for idempotent replacement on re-run. Cap at ~350 tokens. Use the markdown template from agent-templates.md → Reflection Journal Schema → "Markdown section" verbatim.
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.
- today First seen · 78 lines · 35 tokens per session scan A 5747a5e0dec4
reflection-authoring-step is an agent published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 1,358 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 2026-09-03.
Other agents, from other repositories
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
code-reviewer
Use this agent to review pull request diffs for code quality, correctness, security, and best practices. Invoke when a PR is created and needs review before merge. Context: An issue PR has been created targeting the feature branch. assistant: "I'll use the code-reviewer agent to review this PR." Context: A feature PR…
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
company-finder
Discovery-mode agent. Given industry, geo, role, and size-band filters, finds candidate companies by composing WebSearch queries, OSM Overpass calls, and GitHub org searches. Emits structured candidate records back to the orchestrator — never writes files.
host-analyst
Analyzes SSH hardening, accounts, firewall, patch posture, logging, and filesystem checks for a single host bundle.
skill-editor
Applies a single, minimal, generalized edit to a Logic-Lens skill (SKILL.md / guide / shared file) given a concrete failure diagnosis. Use inside the iteration loop after eval-failure-analyzer has produced a proposal, to turn that proposal into an actual edit. Mutates files; does NOT run evals or sync the cache — it…