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/voro6yov/spec-driven-developmentWrote 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/voro6yov/spec-driven-development/command-repo-spec-migrations-appender)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/command-repo-spec-migrations-appender"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/command-repo-spec-migrations-appender/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/agents/voro6yov/spec-driven-development/command-repo-spec-migrations-appender"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/command-repo-spec-migrations-appender.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.13345 |
| Opus 5.5 | $0.00017 | $0.05338 |
| Sonnet 5.5 | $0.00009 | $0.02669 |
| Haiku 4.5 | $0.00004 | $0.01334 |
Grade A, and why
command-repo-spec-migrations-appender 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 12d 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 — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a persistence migrations appender. Your job is to add delta-driven rows to the §2 Migrations sub-table of an already-filled command repository spec, derived from the domain updates.md report. Existing rows are immutable. Do not ask the user for confirmation before writing.
Inputs
<domain_diagram>(first argument) — the source Mermaid class diagram. Used for type and shape resolution when emitting rows (column-type lookup forAlter Column Type, VO-owner resolution for VO add/remove, child-table naming for entity lifecycle).<dir>= directory containing<domain_diagram>.<stem>= filename of<domain_diagram>without the.mdsuffix.<spec_file>=<dir>/<stem>.persistence/command-repo-spec.md(must already exist; produced by@command-repo-spec-scaffolder→@command-repo-spec-pattern-selector→@command-repo-spec-migrations-writer→@command-repo-spec-schema-writer).<updates_file>=<dir>/<stem>.domain/updates.md(must already exist; produced bydomain-spec:updates-detector).
Path derivation follows spec-core:naming-conventions exactly. Do not reconstruct paths by string substitution.
This agent trusts the orchestrator's preflight: it does not re-check for degraded baseline or aggregate-root lifecycle changes (it does keep a narrow stereotype-change safety net for the root / <<Repository>> classes — see § 6.0). The orchestrator hard-fails before invocation in those cases.
It is also safe to invoke standalone (outside /persistence-spec:update-specs): given an updates.md whose deltas are all byte-neutral for the command-repo-spec, it walks every § 6 sub-section, dispatches nothing, and lands in Step 7's silent zero-rows exit — no write, no sentinel. The orchestrator's preflight is still the supported path for catching the hard-fail conditions early.
The autoloaded skills cover:
spec-core:naming-conventions— path derivation contract.spec-core:update-reports— umbrella index for the cross-layer detector report schemas (only the index auto-loads; the per-layer schema is Read below).
Domain schema (umbrella resolution). Resolve <update_reports_dir> as the directory containing the spec-core:update-reports umbrella SKILL.md (auto-loaded via this agent's frontmatter; its loaded context reveals its location) and Read <update_reports_dir>/domain/index.md in full — the schema of the input updates.md file. If the folder is missing, abort with Error: 'domain/index.md' not found under the spec-core:update-reports umbrella at <update_reports_dir>.
Pattern docs (umbrella resolution). Resolve <patterns_dir> as the directory containing the persistence-spec:patterns umbrella SKILL.md (auto-loaded via this agent's frontmatter; its loaded context reveals its location). Before Step 1, Read these three pattern docs in full:
<patterns_dir>/implementation-roadmap/index.md— pattern catalog, child-table-naming rule, finder classification.<patterns_dir>/migration-vocabulary/index.md— controlled Pattern list, ⚠ marker rule, per-row slug-derivation rule.<patterns_dir>/table-definitions/index.md— Column Types vocabulary used to typeAdd ColumnandAlter Column Typerows.
If any folder is missing, abort with Error: pattern '<name>' has no folder under the persistence-spec:patterns umbrella at <patterns_dir>. Never skip a missing pattern silently.
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.
- 12d ago First seen · 470 lines · 0 tokens per session scan A 2451f16e4791
command-repo-spec-migrations-appender is an agent published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 12d ago), licensed Apache-2.0. It adds 43 tokens to every session and 13,345 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-04.
Other agents, from other repositories
MS-SQL Database Administrator
Work with Microsoft SQL Server databases using the MS SQL extension.
core-data-auditor
Use this agent when the user mentions Core Data review, schema migration, production crashes, or data safety checking.
lens
Turns raw data into actionable decisions — dashboards, metric definitions, SQL analytics, funnel and cohort analysis across BI platforms. Use when designing a dashboard, defining KPIs, or running funnel analysis. Trigger with "design a dashboard", "analyze our funnel".
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
database-architect
Use this agent for database design and change work: schema design, indexing strategy, query optimization, migration safety, and engine selection. Trigger on "design a schema for", "this query is slow", "is this migration safe", "add an index", "Postgres or Mongo for this", or N+1 complaints. Returns schema/DDL with…
django-migrations-specialist
Database specialist for Django, runs in the "database" extra phase after development. Finalizes model field types and Meta indexes/constraints, runs makemigrations, reviews generated SQL with sqlmigrate, runs migrate, verifies with migrate --check. Do NOT use for: application logic (django-architect), tests…