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 instructions/pgsty/pigsty/agents-mdgit clone --depth 1 https://github.com/pgsty/pigstyWhat 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 | $0.04979 | $0.04979 |
| Opus 5 | $0.02490 | $0.02490 |
| Sonnet 5 | $0.00996 | $0.00996 |
| Haiku 4.5 | $0.00498 | $0.00498 |
Grade C, and why
pigsty AGENTS.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- rm -rf /pg/* # Delete data directories How it starts
The opening of the file, as written. The whole thing — 486 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pigsty Production Environment - Agent Guide
Pigsty v4.5.0 | PostgreSQL RDS/DBaaS | Apache-2.0
- EN Docs: https://pigsty.io/docs
- CN Docs: https://pigsty.cc/docs
- Expert Support: https://pigsty.io/price ([email protected])
Important Files
pigsty.yml, source of truth of this deployment, always read it to understand current environment.
Sometimes the real state may drift from the config file, especially after manual changes / failover. trust by verify.
files/pki/ca/ca.key - highly sensitive CA private key. Keep it safe, never share it, don't lose it.
If pig cli is available, you can use it to perform operation command with caution. https://pigsty.io/docs/pig
Standard Operating Procedures
Before Any Change
- Identify scope: Which cluster? Which nodes?
- Check current state:
pig pg list, system status - Verify backup:
pig pb info- is backup recent? - Dry run first: Add
--checkto playbook
For Dangerous Operations
- Confirm with user - even in YOLO mode
- Verify backup exists and is recent
- Ask user to type exact target name
- Execute with explicit
-llimit flag
Incident Response
- Read logs first, understand the situation, you can get it from
/pg/log, or query victorialogs API - Check Patroni/HA status
- Do NOT take any action without user confirmation
- Recommend rollback/recovery options before executing
Permission Boundaries
ALWAYS ALLOWED (No confirmation needed)
Read-only operations:
- Read
pigsty.ymlconfiguration file - Read Ansible inventory and playbook files
- Read system monitoring metrics (CPU, memory, disk, network)
- Read PostgreSQL/Patroni cluster status via
pg list,patronictl - Read backup status via
pb info,pgbackrest info - Read service status via
systemctl status - Read logs:
/pg/log/, system journal, nginx access logs - Query monitoring dashboards and Grafana metrics
- Dry-run playbooks with
--checkflag - Read extension catalog and documentation
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 · 486 lines · 4,979 tokens per session scan C e4326e8a0098
pigsty AGENTS.md is an instructions file published in the GitHub repository pgsty/pigsty (5,582 stars, last pushed 8d ago), licensed Apache-2.0. It adds 4,979 tokens to every session, about $0.0249 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
supabase studio-telemetry.instructions.md
Instructions for supabase/supabase, covering studio telemetry review rules, when to flag missing telemetry, feature flag telemetry pattern, event naming and event properties.
supabase studio-composition-patterns.instructions.md
Instructions for supabase/supabase, covering react composition patterns review rules, core principle, when to flag, 1. boolean prop proliferation (high) and 2. render props instead of children (medium).
supabase studio-shortcuts.instructions.md
Instructions for supabase/supabase, covering studio shortcut review rules, core principle, when to flag, preferred pattern and search inputs.
supabase studio-e2e-tests.instructions.md
Instructions for supabase/supabase, covering studio e2e test review rules, selector priority (best to worst), patterns to flag and good practices to encourage.
supabase studio-error-handling.instructions.md
Instructions for supabase/supabase, covering studio error handling review rules, architecture, when to flag, correct usage and key files.
supabase copilot-instructions.md
Instructions for supabase/supabase, covering copilot code review instructions, review policy — read this first, confidence threshold, what not to comment on and what to comment on (priority order).