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 skills add wedabro/bro-skills --skill speckit.databasegit clone --depth 1 https://github.com/wedabro/bro-skillsWrote 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/wedabro/bro-skills/speckit.database)<a href="https://agentmods.dev/skills/wedabro/bro-skills/speckit.database"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.database.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 | $0.00029 | $0.00892 |
| Opus 5 | $0.00015 | $0.00446 |
| Sonnet 5 | $0.00006 | $0.00178 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
speckit.database 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 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.
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
Design data systems that are correct, performant, recoverable, and operable.
Use .agents/knowledge_base/data_schema.md, the feature plan, and the project
constitution. Coordinate with speckit.backend for transaction ownership,
speckit.security for sensitive data, and speckit.devops for runtime setup.
Protocol
0. Preflight
- Identify data classification, ownership, access paths, expected growth, write/read ratio, retention, RPO, RTO, availability target, and production blast radius before choosing a schema or operation.
- Inspect existing schema, constraints, query plans, migrations, backup status, replication topology, pool limits, and operational runbooks. State unknowns rather than treating a backup or replica as verified.
1. Schema and Integrity
- Normalize to 3NF by default; denormalize only for a measured query or scale need and record the consistency/maintenance cost.
- Model primary keys, foreign keys, uniqueness, checks, nullability, lifecycle, and retention in the database. Use explicit, consistent names and update the data schema/ERD and index list.
- Select data types for semantics, range, timezone, precision, and collation; avoid unbounded JSON or text fields where a constrained model is required.
- Define transaction boundaries, isolation, lock ordering, and conflict policy. Use parameterized queries only; prevent N+1 and unbounded reads.
2. Query and Capacity Design
- Index proven WHERE, JOIN, ORDER BY, and tenant access patterns; order composite indexes for actual predicates. Do not add speculative indexes.
- Validate expensive paths with representative
EXPLAIN/query-plan evidence; investigate scans, hot rows, lock waits, large offsets, and write amplification. - Forecast storage, IOPS, connection, replica, and maintenance headroom. Set per-service pool limits and backpressure so clients cannot exhaust the DB.
3. Safe Evolution
- Version migrations and make rollback/forward-recovery behavior explicit. Use expand → backfill in batches → dual read/write when needed → validate → contract for live data changes.
- Assess lock behavior and runtime cost before production DDL; use online or concurrent operations where supported. Separate destructive removal into a later, explicitly approved release.
- Back up and prove a restoration path before destructive/high-impact changes. Never run migration, backfill, delete, or index operation blindly on prod.
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 · 86 lines · 29 tokens per session scan A 3f53806b7b36
speckit.database is a skill published in the GitHub repository wedabro/bro-skills (2 stars, last pushed 12d ago), licensed MIT. It adds 29 tokens to every session and 892 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 skills, from other repositories
offensive-sqli
SQL injection testing skill for offensive security assessments and bug bounty hunting. Covers error-based, UNION-based, boolean/time-based blind, out-of-band, second-order, NoSQL, GraphQL, WebSocket, and JSON-operator SQLi. Includes WAF bypass techniques, database-specific exploitation (MySQL, MSSQL, PostgreSQL…
yida-data-management
A tool for querying, adding, and updating Yida form records, child tables, process records, and task-center data. It keeps ordinary forms and approval workflows on their separate data interfaces.
yida-aggregate-table
A workflow for managing Yida aggregate tables, also called virtual views. These are tables built from related form data rather than ordinary standalone records.
yida-db-seq-fix
A tool for checking and correcting PostgreSQL sequences, which generate automatic numeric IDs for new rows. It is designed for Yida databases after automatic table creation or data migration.
doris-repo-review
Review an Apache Doris PR from a local clone with the same multi-agent, shared-ledger convergence workflow as the CI Code Review Runner. Use when the user supplies a PR to /doris-repo-review, asks to review a Doris PR locally, or asks for the CI-style review flow. Safely align only the current worktree to the exact PR…
doris-architecture-advisor
Workload-aware architecture design for Apache Doris. MUST USE when designing data architectures, choosing between data models, planning ingestion strategies, sizing clusters, or translating business requirements into Apache Doris system designs. Complements doris-best-practices with decision frameworks and…