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/bo0tzz/pgmqtt/agents-mdgit clone --depth 1 https://github.com/bo0tzz/pgmqttWrote 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/instructions/bo0tzz/pgmqtt/agents-md)<a href="https://agentmods.dev/instructions/bo0tzz/pgmqtt/agents-md"><img src="https://agentmods.dev/badge/instructions/bo0tzz/pgmqtt/agents-md.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 | $0.02016 | $0.02016 |
| Opus 5 | $0.01008 | $0.01008 |
| Sonnet 5 | $0.00403 | $0.00403 |
| Haiku 4.5 | $0.00202 | $0.00202 |
Grade A, and why
pgmqtt AGENTS.md 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Operational notes for working in this repo as an autonomous agent (Claude Code or otherwise). Designed as a load-bearing playbook: read it before your first commit, link it from PRs that follow non-obvious workflows.
Validation tier model
Three tiers, additive (tier3 ⊃ tier2 ⊃ tier1). Wall-clock + exact bug
coverage are documented in scripts/validate-timings.md.
Short version:
| Tier | When to run | Wall clock | Run command |
|---|---|---|---|
| tier1 | After every code change | ~10s | make validate TIER=tier1 |
| tier2 | Before commit / before PR | ~6m | make validate TIER=tier2 PAHO=/tmp/paho-testing |
| tier3 | Before tag / weekly nightly | ~12–18m | make validate TIER=tier3 PAHO=/tmp/paho-testing |
What each tier closes that the prior tier misses:
- tier1 — compile / vet / race-light unit tests / chart lint+template. Catches static bugs, helm rendering issues (typoed values keys, scientific- notation in int fields), small-package data races.
- tier2 — full unit suite against a testcontainer Postgres + paho v3+v5 conformance against a single broker. Catches SQL path regressions and MQTT protocol shape bugs (reason codes, retain, will-delay, takeover ordering).
- tier3 — multi-broker paho via kind + 60s soak smoke. Catches cross- pod fanout bugs, deploy-shape regressions (helm-rendered manifests applied to a real apiserver), sustained-load issues.
In CI:
ci.yml— covers tier1's surface on every PR (vet, test, test-race, helm lint, kind-based smoke). Already green is your gate to merge. Dependency scanning lives in its owngovulncheck (deps)job so an upstream advisory doesn't read as a test failure; it still gates merge.conformance-nightly.yml— runs tier2 daily at 03:00 UTC. Doesn't gate PRs; informational regression detector.soak-weekly.yml— runs an in-cluster soak (and tier3 paho multi-broker, best-effort) Mondays 04:00 UTC. Fails on any QoS≥1 loss/dups.
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 Changed · +1 lines · +27 tokens per session 886d9701713d
- 5d ago First seen · 167 lines · 1,989 tokens per session scan A 48b83555f598
pgmqtt AGENTS.md is an instructions file published in the GitHub repository bo0tzz/pgmqtt (10 stars, last pushed yesterday), licensed MIT. It adds 2,016 tokens to every session, about $0.0101 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).