Routa is a workspace-based coordination platform for delivering software with multiple AI agents, keeping goals, tasks, sessions, traces, evidence, and review decisions visible on a shared board. It is intended for teams managing agent-assisted development across web and desktop applications. The catalogue contains skills and instructions for working with Routa's delivery workflows.
Borrowing it
Nothing to install: this file belongs to phodal/routa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/phodal/routa/main/.claude/skills/evolution-architecture-review/SKILL.mdgit clone --depth 1 https://github.com/phodal/routaWrote 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/skills/phodal/routa/evolution-architecture-review)<a href="https://agentmods.dev/skills/phodal/routa/evolution-architecture-review"><img src="https://agentmods.dev/badge/skills/phodal/routa/evolution-architecture-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/phodal/routa/evolution-architecture-review"><img src="https://agentmods.dev/badge/skills/phodal/routa/evolution-architecture-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 129 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 5.1 | $0.00072 | $0.00908 |
| Opus 5 | $0.00036 | $0.00454 |
| Sonnet 5 | $0.00014 | $0.00182 |
| Haiku 4.5 | $0.00007 | $0.00091 |
Grade A, and why
evolution-architecture-review 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Assess how safely this codebase can evolve, using parallel analysis where possible.
Do not give generic architecture advice. Ground every conclusion in repository evidence.
Default to read-only analysis. Do not edit code unless the user explicitly changes the task from review to implementation.
Default Mode
Prefer a 4-lens review in parallel. If subagents or Task are available, use them. If not, run the same lenses sequentially yourself.
Lens 1: System shape and boundaries
- Identify major modules, ownership boundaries, and dependency direction.
- Look for hidden coupling, duplicated semantics, and unclear seams.
Lens 2: Runtime flow and operability
- Inspect task flow, orchestration, state transitions, control-plane behavior, and failure visibility.
- Focus on whether the system is observable and debuggable during change.
Lens 3: Fitness and verification
- Inspect hard gates, tests, contract checks, parity checks, and evidence loops.
- Determine whether the architecture has executable constraints or mostly human judgment.
Lens 4: Evolution path
- Propose incremental change steps, rollback-friendly sequencing, and smallest viable improvements.
- Avoid rewrite-first recommendations.
Starting Points
Read these first unless the user narrows scope:
AGENTS.mddocs/ARCHITECTURE.mddocs/product-specs/FEATURE_TREE.mddocs/fitness/README.mddocs/blog/routa-kanban-agent-team-management.mddocs/blog/harness-fitness-function.mdsrc/core/orchestration/src/core/kanban/src/core/specialists/crates/routa-core/src/workflow/crates/routa-server/src/
Then expand only where evidence requires it.
Scope Hygiene
Treat the main repository tree as authoritative. Unless the user explicitly asks otherwise, ignore duplicate or generated trees such as:
.worktrees/.routa/repos/node_modules/.next/target/out/dist/coverage/tmp/test-results/
When using Glob, Grep, or Task, state these exclusions explicitly so subagents do not waste time or cite mirrored files.
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.
- 9d ago First seen · 131 lines · 72 tokens per session scan A 894b56f2992c
evolution-architecture-review is a skill published in the GitHub repository phodal/routa (1,810 stars, last pushed 26d ago), licensed MIT. It adds 72 tokens to every session and 908 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…