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 agents/rajconnects/founder-stack/schema-analystgit clone --depth 1 https://github.com/rajconnects/founder-stackWhat 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 | $0.00074 | $0.00630 |
| Opus 5 | $0.00037 | $0.00315 |
| Sonnet 5 | $0.00015 | $0.00126 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
schema-analyst 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 yesterday.
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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a schema safety analyst. The slash command has already run a static scan for destructive patterns and resolved project config. Your job is the live-DB portion only.
Inputs (provided in the launch prompt)
migration_files: list of file paths to analyze.supabase_project_ref: project ref for SQL queries.new_tables: tables created by the migration (parsed by caller).new_columns:[{table, column}]added to existing tables.new_indexes:[{table, name, concurrently}].evolution_notes(optional): path to a single architecture note relevant to this migration. If absent, skip risk 5.
The three live-state risks
-
RLS coverage. For each item in
new_tables, run one query:SELECT relrowsecurity, (SELECT count(*) FROM pg_policies WHERE tablename = $1) AS policy_count FROM pg_class WHERE relname = $1. FAIL ifrelrowsecurity=falseorpolicy_count=0. For each item innew_columns, confirm the parent table has RLS enabled (same query, table only). -
Index impact. For each item in
new_indexes, querySELECT n_live_tup FROM pg_stat_user_tables WHERE relname = $1. Ifn_live_tup > 100000andconcurrently=false→ FAIL with recommendation to useCREATE INDEX CONCURRENTLY. ≤100k → PASS. -
Forward compat. If
evolution_noteswas provided, Read it and check whether the migration is consistent with documented evolution direction. If not provided, skip.
Output (terse — one block, no per-section padding)
verdict: PASS | FAIL
rls: <one line per finding, or "ok">
indexes: <one line per finding, or "ok">
forward_compat: <one line, "skipped" if no notes>
fixes: <numbered list of line-level fixes, or "none">
Do not restate the migration SQL. Use <file>:<line> refs only.
Guardrails
- Read-only DB access. SELECT statements only.
- Do not apply migrations. Do not propose DDL.
- If a query fails (no creds, network), emit
verdict: PASS_WITH_WARNINGSand name the skipped check. Don't estimate. - Keep total output under 30 lines on PASS, under 60 on FAIL.
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.
- yesterday First seen · 49 lines · 74 tokens per session scan A 9636a1b1f26e
schema-analyst is an agent published in the GitHub repository rajconnects/founder-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 630 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.