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 skills/r5rana/agentware/safe-migrationnpx skills add r5rana/agentware --skill safe-migrationgit clone --depth 1 https://github.com/r5rana/agentwareWrote 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/r5rana/agentware/safe-migration)<a href="https://agentmods.dev/skills/r5rana/agentware/safe-migration"><img src="https://agentmods.dev/badge/skills/r5rana/agentware/safe-migration.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 | $0.00213 | $0.03119 |
| Opus 5 | $0.00106 | $0.01559 |
| Sonnet 5 | $0.00043 | $0.00624 |
| Haiku 4.5 | $0.00021 | $0.00312 |
Grade A, and why
safe-migration 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 5d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safe Migration
Portable Agent Skill (agentskills.io open standard). The YAML frontmatter above is the spec-compliant contract:
nameequals the folder name anddescriptionis the routing text. The body is HARNESS-AGNOSTIC — no hardcoded invocation syntax, no harness-only frontmatter. It drives the project's own migration tooling (Drizzle, Prisma, Alembic, Rails, Flyway, raw SQL, a config rewrite, or a file move), needs no new dependency, and installs nothing.
When to invoke: any time a change rewrites PERSISTED state — a database schema or data migration, a backfill or bulk update, a column/table rename or drop, a data-model refactor, a config-format change with on-disk state, or a file/directory restructure that other code reads. Invoke BEFORE writing the migration, while the approach is still a choice. For verifying a single endpoint after the fact use
backend-verification; for designing the new model securely usesecure-by-design/threat-modeling; this skill is the "how do I change live state without losing data or being unable to undo it" gate.
Why this skill exists
The dangerous property of a migration is that it is a write to data you cannot
re-derive. A bug in a handler can be patched; a DROP COLUMN that ran against the
only copy of the data cannot. agentware's rules already forbid acting destructively
or irreversibly without confirmation (R-AUTO-02) and require read-after-write proof
for mutations (R-VERIFY-04) — this skill is how you satisfy both for stateful
changes. The failures it prevents are the expensive ones: an in-place rename that
breaks the still-running old code mid-deploy, a backfill that half-finished and left
rows in two shapes, a "recreate everything" migration auto-generated by a diff tool
that fails because the tables already exist, and the migration that worked but had
no rollback when the app turned out to depend on the old column.
Core principle — expand, then contract
Prefer expand-contract (a.k.a. parallel-change) over a breaking in-place edit. It keeps old and new readers working at every step, so a deploy never has a moment where running code sees a shape it doesn't understand, and every step is independently revertible:
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.
- 5d ago First seen · 225 lines · 213 tokens per session scan A 53a4e037df54
safe-migration is a skill published in the GitHub repository r5rana/agentware (24 stars, last pushed 18d ago), licensed Apache-2.0. It adds 213 tokens to every session and 3,119 once invoked, about $0.0011 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
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
debugging
How to debug tursodb using Bytecode comparison, logging, ThreadSanitizer, deterministic simulation, and corruption analysis tools.
sdk-design
Doctrine for designing and evolving any SDK Grida ships — TypeScript, Rust, or otherwise. "SDK" here means a surface that crosses a foreign-or-foreign-treated boundary: published packages, separately-versioned consumers, FFI bindings, public-by-design modules. An SDK's job is to refuse; a strict, honest surface…
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.