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 commands/authzed/authzed-marketplace/migrate-testsgit clone --depth 1 https://github.com/authzed/authzed-marketplaceWrote 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/authzed/authzed-marketplace/migrate-tests)<a href="https://agentmods.dev/commands/authzed/authzed-marketplace/migrate-tests"><img src="https://agentmods.dev/badge/commands/authzed/authzed-marketplace/migrate-tests.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 | $0.00018 | $0.10160 |
| Opus 5 | $0.00009 | $0.05080 |
| Sonnet 5 | $0.00004 | $0.02032 |
| Haiku 4.5 | $0.00002 | $0.01016 |
Grade A, and why
migrate-tests 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 3d 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 — 569 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate Tests
Phase 5 of the migration pipeline: convert a source system's test fixtures and assertions
into SpiceDB validation YAML, and validate every emitted file with zed validate.
This command's job is to convert, following the pack's test-mapping reference exactly,
and to decide as little as possible while doing it. Where a genuine judgment call remains --
which candidate test file to convert, how to resolve a same-object/different-relation
collision -- it is a human call, and this command asks with AskUserQuestion and records the
answer directly in migration-plan.md's narrative Deferred / manual section -- a
file-selection or collision-scenario choice has no migration-map.json counterpart, unlike
phase 0's own decisions, which live in the JSON's decisions key and are only rendered to the
plan (findings-report.md's "Two groups of sections, one rule each").
This command has no gate of its own, reduced or otherwise. Unlike
/spicedb-dev:migrate-schema, which stays independently runnable for schema-only work
because it can decide phase 1's own inputs from the model alone, test conversion is a pure
consumer of migration-plan.md and migration-map.json -- every rewrite rule below is
"look this name up in the map", not a decision this command could make standalone. If
migration-plan.md is missing, or was authored by the reduced inline gate rather than the
full one, this command halts and routes to /spicedb-dev:migrate rather than inventing a
gate to fill the gap.
Outputs, written to [output-dir] (default: the directory phase 0 wrote migration-map.json to, i.e. the project being migrated -- not the shell's current working directory):
validation.yaml-- the canonical converted output for the selected source test file.validation-<scenario>.yaml-- one additional file per losing scenario, written only when step 5's mechanism-B collision fires.migration-map.json-- updated in place with this run'sphase_status["5"](step 8.1) -- the single machine-readable record of that status.migration-plan.md-- regenerated in place: every advisory finding, collision record, and file-selection decision this run produced is appended directly to the narrative Deferred / manual section (step 8.2), and every other rendered section is rebuilt from the just-updatedmigration-map.json(step 8.3).
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.
- 3d ago First seen · 569 lines · 18 tokens per session scan A 28871f025f59
migrate-tests is a command published in the GitHub repository authzed/authzed-marketplace (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 18 tokens to every session and 10,160 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.