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/luisfelipemoro/harness-devkit/database-migrationnpx skills add LuisFelipeMoro/Harness-devkit --skill database-migrationgit clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkitWhat 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 | $0.00072 | $0.00505 |
| Opus 5 | $0.00036 | $0.00253 |
| Sonnet 5 | $0.00014 | $0.00101 |
| Haiku 4.5 | $0.00007 | $0.00051 |
Grade A, and why
database-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 2d 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.
What it actually says
A migration must be additive-only in one file, must ship a down migration that fully reverses the up, and must never drop-and-replace or rename a column directly. Any DDL on a table over 1M rows must carry a lock strategy.
Contract
- Input: a requested schema change against a known database.
- Output: an up/down migration pair plus a falsified migration test, following the patterns in
references/migration-patterns.md. - Tool boundary: schema-only changes; expand-contract spreads risky changes across separate deploys, never one file.
- Done when: the four assertions are specified up front, the migration and its test are written, the test is falsified against the pre-migration schema, and the pre-handoff checklist passes.
Steps
- Classify the change against the risk table in
references/migration-patterns.mdto pick a strategy. - Specify the four assertions the test will make — up applies, down reverses, up is idempotent, data is safe — before writing SQL. They are enumerated in
references/test-and-checklist.md. - Write the up/down SQL from the matching template in
references/migration-patterns.md. - Write the migration test asserting those four things, then falsify it: run it against the pre-migration schema (or comment out the
upbody) and confirm each assertion fails, then restore. A migration test that passes without the migration is asserting nothing. Worked example inreferences/test-and-checklist.md. - For large tables, apply
CONCURRENTLYor an explicit session lock timeout perreferences/migration-patterns.md. - Confirm the pre-handoff checklist in
references/test-and-checklist.mdbefore handing off.
References
references/migration-patterns.md— principles, change-classification table, up/down templates, large-table and lock-timeout patterns.references/test-and-checklist.md— the four assertions, the migration test, its falsification step, and the pre-handoff checklist.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 25 lines · 72 tokens per session scan A e86c4744bf6d
database-migration is a skill published in the GitHub repository LuisFelipeMoro/Harness-devkit (10 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 505 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.