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.
git clone --depth 1 https://github.com/alinaqi/maggyWrote 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/commands/alinaqi/maggy/route-eval)<a href="https://agentmods.dev/commands/alinaqi/maggy/route-eval"><img src="https://agentmods.dev/badge/commands/alinaqi/maggy/route-eval.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 5.1 | $0.00000 | $0.00974 |
| Opus 5 | $0.00000 | $0.00487 |
| Sonnet 5 | $0.00000 | $0.00195 |
| Haiku 4.5 | $0.00000 | $0.00097 |
Grade A, and why
route-eval scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
BOOTSTRAP_DIR="$(cat ~/.claude/.bootstrap-dir)" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/route-eval — Evaluate a project and set its routing profile
Analyze the current project's structure and your past routing history, then
recommend a per-project routing profile — e.g. a small, low-risk project can send
everything through one cheap model (like glm-5.2), while security-sensitive files
always escalate to Claude.
The profile is stored privately, per-machine at
~/.claude/projects/<encoded-cwd>/routing.yaml (never committed) and overrides the
global ~/.maggy/routing.yaml for work in this project. It stays fully hand-editable.
Usage
/route-eval — evaluate + show a recommendation, write only after you confirm
/route-eval show — print the project's current profile (if any)
/route-eval --model <id> — use a different cheap default for the simple profile
Steps
Resolve the Maggy package from the bootstrap pointer and evaluate:
BOOTSTRAP_DIR="$(cat ~/.claude/.bootstrap-dir)"
RUN="PYTHONPATH=$BOOTSTRAP_DIR/maggy python3 -m maggy.route_eval"
1. Evaluate + recommend (default; never writes)
eval "$RUN plan --cwd \"$(pwd)\" --model glm-5.2"
Present the JSON to the user in plain language:
- profile —
simple(one cheap model),balanced(complexity ladder), orcritical(security surface / large repo → premium tiers). - default_model — the model everything routes to under
simple. - escalate_paths — globs that always jump to Claude (auth/payments/billing).
- _meta.evidence — why this profile: file count, languages, security surface, and the dominant tier in your routing history.
Explain the trade-off in one line (cost vs. safety), then ask: write this profile?
2. Write it (only on explicit confirmation)
eval "$RUN apply --cwd \"$(pwd)\" --model glm-5.2"
Report the written path and remind the user it is private (not committed) and can be edited by hand — profile, default model, and escalation rules are all adjustable.
3. Show the current profile
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.
- 8d ago First seen · 97 lines · 0 tokens per session scan A 0fcdaa98d1bd
route-eval is a command published in the GitHub repository alinaqi/maggy (705 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 974 tokens. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
crystallize
Transform verbose SOPs into high-performance agentic prompts via principled compression. Use when user says "/crystallize", "compress this prompt", "make this more agentic".
ai-feature-eval-harness
Design an evaluation plan for a product AI feature (LLM- or model-backed output): measurable success criteria, a held-out labeled eval dataset shape, per-criterion grading (code-based first, then LLM-based for nuanced judgment), and a pass threshold, then persist as AIEVALPLAN.md. Use when the task ships or changes a…
gentle-sdd-ff
Fast-forward all SDD planning phases — proposal through tasks.
sdd-explore
Explore and investigate an idea or feature — reads codebase and compares approaches.
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].