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 elevanaltd/HestAI-MCP --skill supabase-operationsgit clone --depth 1 https://github.com/elevanaltd/HestAI-MCPWrote 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/elevanaltd/hestai-mcp/supabase-operations)<a href="https://agentmods.dev/skills/elevanaltd/hestai-mcp/supabase-operations"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/supabase-operations/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/elevanaltd/hestai-mcp/supabase-operations"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/supabase-operations.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00076 | $0.01684 |
| Opus 5 | $0.00038 | $0.00842 |
| Sonnet 5 | $0.00015 | $0.00337 |
| Haiku 4.5 | $0.00008 | $0.00168 |
Grade A, and why
supabase-operations 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
===SUPABASE_OPERATIONS=== META: TYPE::SKILL VERSION::"1.1.0" STATUS::ACTIVE PURPOSE::"Supabase operational knowledge: migrations, RLS optimization, MCP benchmarks, ADR-003 compliance, and CI-proven ordering invariants"
§1::CAPABILITIES_SUPPORTING_DOCUMENTATION
MIGRATION_VALIDATION::migration-protocols.oct.md::[ 7_step_workflow, backwards_compatible_schema_changes, multi_app_deployment_safety, CI_gated_deployment[preferred_over_direct_MCP] ]
RLS_OPTIMIZATION::rls-optimization.oct.md::[ proven_patterns→sub_50ms_query_performance, InitPlan_optimization, policy_consolidation ]
MCP_BENCHMARKS::mcp-benchmarks.oct.md::[ performance_characteristics, best_practices, production_measurements ]
ADR_003_COMPLIANCE::adr-003-compliance.oct.md::[ backwards_compatible_migration_governance, verification_checklist ]
STATE_TRACKING::state-tracking.oct.md::[ local_remote_sync_validation, database_state_awareness_procedures ]
§2::INVOCATION_TRIGGERS
MIGRATION_OPERATIONS::[ before_applying_migrations→validation_checklist, after_schema_changes→compliance_verification, debugging_migration_divergence, CI_deployment_flow→PR_with_deploy_migrations_label ]
RLS_DESIGN::[ optimizing_slow_queries_with_RLS, designing_new_security_policies, benchmarking_RLS_performance_impact ]
DATABASE_OPERATIONS::[ selecting_appropriate_MCP_tools, validating_current_database_state, checking_security_performance_advisors ]
COMPLIANCE::[ verifying_ADR_003_backwards_compatibility, multi_app_testing_requirements, emergency_rollback_procedures ]
§3::TOOL_RESTRICTIONS_READ_ONLY_INSPECTION
ALLOWED_TOOLS::[ Read::"Access local migration files and documentation", mcp__supabase__list_tables::"Inspect current schema structure", mcp__supabase__list_extensions::"Verify installed extensions", mcp__supabase__list_migrations::"Compare local/remote migration state", mcp__supabase__get_advisors::"Check security/performance compliance" ]
SECURITY_JUSTIFICATION::"Skills guide operations but don't mutate state. Write operations (apply_migration, execute_sql) remain with authorized agents."
§4::INTEGRATION
CONSULTED_BY::[ technical-architect[domain_authority_with_BLOCKING], implementation-lead[migration_execution], technical-architect[schema_design] ]
PROVIDES::[ migration_validation_checklists, RLS_optimization_patterns, MCP_tool_selection_guidance, compliance_verification_procedures, CI_deployment_guidance[gated_auto_deploy] ]
§5::CI_DEPLOYMENT_AWARENESS
PREFERRED_FLOW::[ 1::create_PR_with_migrations, 2::add_deploy_migrations_label, 3::CI_validates_locally, 4::merge_triggers_production_deploy, 5::audit_log_entry_created ]
DIRECT_MCP_APPLICATION::[ STATUS::fallback_only, WHEN::CI_unavailable_OR_emergency, REQUIREMENT::always_create_local_file_first, WARNING::bypasses_CI_validation ]
CI_REFERENCE::[ WORKFLOW::".github/workflows/ci.yml (deploy-migrations job)", SECRET::"SUPABASE_ACCESS_TOKEN required", LABEL::"deploy-migrations", DR_PLAYBOOK::".hestai/state/context/docs/001-OPS-DISASTER-RECOVERY-PLAYBOOK.md" ]
§6::TYPES_REGEN_AND_TEST_VALIDATION // RCA-derived ordering invariants. Three process gaps caused CI failures in consuming repos. // Encode as MUST/NEVER constraints — not advisory.
TYPES_REGEN_ORDERING::[ SEQUENCE::"supabase db reset → gen types → THEN pgTAP tests [NEVER reverse]", INVARIANT::"Generate types ONLY from clean post-reset DB state", VIOLATION_CAUSE::"pgTAP CREATE EXTENSION outside BEGIN...ROLLBACK persists pgtap into public schema", SYMPTOM::"Generated types pick up pgTAP symbols (e.g. 146 extra) that CI rejects on clean reset", MUST::"Run supabase db reset then immediately gen types before any pgTAP execution", NEVER::"Generate types from a DB that has had pgTAP tests run against it" ]
DROPPED_OBJECT_SWEEP::[ TRIGGER::"Migration drops OR renames a constraint, column, or any named DB object", REQUIRED_ACTION::"grep supabase/test*/ corpus for the dropped object name", SCOPE::"Entire supabase/test*/ directory tree — all test files", VIOLATION_CAUSE::"pg_depend sweep finds column dependents but misses TEST CORPUS assertions about the dropped constraint", SYMPTOM::"Pre-existing expectation test fails against CI clean state", MUST::"Update any test assertions referencing the dropped/renamed object in the same PR as the migration", NEVER::"Ship a migration that drops/renames a named object without grepping the test corpus first" ]
What ships with it
10 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.
- 8d ago First seen · 177 lines · 76 tokens per session scan A 08c3740f28d9
supabase-operations is a skill published in the GitHub repository elevanaltd/HestAI-MCP (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 76 tokens to every session and 1,684 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 2026-09-03.
Other skills, from other repositories
neon
Use when you have picked Neon (serverless Postgres) and need to connect correctly from a serverless or edge runtime, wire database branching into dev, preview and CI, or stop being burned by scale-to-zero cold starts and pooler limits — including choosing HTTP versus WebSocket connections and pooled versus direct…
neon
Neon serverless PostgreSQL with branching. Use for serverless Postgres.
alloydb-basics
Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB Model Context Protocol (MCP) tools for automated database operations. Use when creating, configuring, or administering AlloyDB databases. Do NOT use for general PostgreSQL instances (e.g. Cloud SQL) or other GCP databases.
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
db-repair
Auto-fix gbrain's Postgres access so the brain stays available. When any gbrain command or MCP tool result carries a GBRAINDBACCESS marker (or an operator reports the brain database is down), run the hardcoded gbrain db-repair ladder: diagnose, apply the safe tier, verify. The action is ALWAYS the hardcoded command …
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…