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/zevtos/agentpipe/dbgit clone --depth 1 https://github.com/zevtos/agentpipeWhat 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 | $0.00022 | $0.00745 |
| Opus 5 | $0.00011 | $0.00373 |
| Sonnet 5 | $0.00004 | $0.00149 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
db 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are orchestrating a database schema change. Database changes are the most dangerous changes in a codebase — a bad migration can cause downtime or data loss. Follow this pipeline rigorously.
Context
@CLAUDE.md
Change Request
$ARGUMENTS
Pipeline
Step 1: Design (DBA Agent)
Run the dba agent:
"Database change needed: $ARGUMENTS
Read the existing schema and codebase, then:
- Design the schema change with exact SQL
- Classify: additive-only (safe) or breaking change (requires expand-contract)
- For breaking changes: provide the full expand-contract plan (expand → migrate → contract)
- Lock analysis: which locks are acquired, for how long, impact on concurrent queries
- Index changes needed for new query patterns
- Rollback plan: exact steps to undo if something goes wrong
- Data migration plan if existing data needs transformation (batch size, checkpointing)
- Impact on application code (which queries/models need updating)"
Present to user. Ask: "This migration plan look correct? Any concerns about the data transformation?" Wait for confirmation.
Step 2: Implementation
Based on the DBA output:
- Create migration file(s) with exact SQL from the DBA plan
- For expand-contract: create SEPARATE migration files for each phase
- Update application code (models, queries, DTOs) to work with both old and new schema during transition
- Add feature flag for read/write switching if applicable
- Add data backfill script if needed (with batching, checkpointing, replication lag monitoring)
Step 3: Review (Reviewer Agent)
Run the reviewer agent:
"Review this database migration for: $ARGUMENTS
Key checks:
- Migration SQL matches the DBA-approved plan
- lock_timeout is set before every DDL statement
- CONCURRENTLY used for index creation (PostgreSQL)
- NOT VALID + VALIDATE pattern for constraints
- Batch size appropriate for data migrations
- Rollback plan is executable
- Application code handles both old and new schema during transition
- No N+1 queries introduced by schema changes"
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 · 78 lines · 22 tokens per session scan A 465e65ba4642
db is a command published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 745 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 2026-08-30.
Other commands, from other repositories
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.