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/intrinsec/protoc-gen-psql/agents-mdgit clone --depth 1 https://github.com/Intrinsec/protoc-gen-psqlWrote 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/intrinsec/protoc-gen-psql/agents-md)<a href="https://agentmods.dev/instructions/intrinsec/protoc-gen-psql/agents-md"><img src="https://agentmods.dev/badge/instructions/intrinsec/protoc-gen-psql/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 | $0.03953 | $0.03953 |
| Opus 5 | $0.01976 | $0.01976 |
| Sonnet 5 | $0.00791 | $0.00791 |
| Haiku 4.5 | $0.00395 | $0.00395 |
Grade A, and why
protoc-gen-psql 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 4d 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 — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — protoc-gen-psql
Operational contract for AI agents (Claude Code, Copilot, Gemini) and human contributors. Source of truth for tooling, workflow, and out-of-scope items.
- Tier: B (shared internal tool, no runtime SLA)
- Type: 2 — Go CLI (
protocplugin binary) - Module:
github.com/intrinsec/protoc-gen-psql - Purpose: generate PostgreSQL DDL files from protobuf message definitions
- Go:
go 1.25.0directive,toolchain go1.26.3. Entry pointmain.goregistersPSQLify()againstprotoc-gen-star. Build artifact:bin/protoc-gen-psql.
Language
Default agent response: English, even if user writes French. French response only when user explicitly asks French.
Caveman compression mandatory for all conversational responses (default level: full).
Code blocks, commit messages, PR descriptions, security warnings, irreversible-action
confirmations stay normal prose (Caveman auto-clarity rules). Do not disable Caveman unless
user says "stop caveman" or "normal mode".
HARD RULE: all code, comments, identifiers, doc strings, commit messages, ADRs, technical docs in English — every project type, regardless of team spoken language. User-facing strings + UI copy exempt — match audience language.
Workflow Skills (mandatory)
Every agent session in this repo must load + apply these skill packs:
- superpowers — process discipline (
brainstorming,writing-plans,executing-plans,test-driven-development,systematic-debugging,verification-before-completion,requesting-code-review). - caveman — response compression (see Language section).
Pack missing? Install per iagen-dev INSTALL.md before work.
Session start gate
Before any response, clarification, repository inspection, shell command, or file edit:
run superpowers:using-superpowers first, then run caveman so compression is active
for every response. Use superpowers:using-superpowers to decide which additional
skills apply, then follow the selected skill workflows.
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.
- 4d ago First seen · 335 lines · 3,953 tokens per session scan A bf9d7b8683ba
protoc-gen-psql AGENTS.md is an instructions file published in the GitHub repository Intrinsec/protoc-gen-psql (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 3,953 tokens to every session, about $0.0198 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 instructions, from other repositories
prest copilot-instructions.md
Copilot instructions for prest/prest, covering copilot instructions for prest go backend, project scope, core engineering principles, solid principles for go and s — single responsibility.
GoSQLX CLAUDE.md
Instructions for ajitpratap0/GoSQLX, covering claude.md, project overview, architecture, core components and token processing pipeline.
faucet CLAUDE.md
Claude Code instructions for faucetdb/faucet, covering faucet - claude.md, what is this?, architecture, project structure and key commands.
PulseWeaver AGENTS.md
AGENTS.md instructions for DiegoGuidaF/PulseWeaver, covering agents.md, project overview, database migrations, commands and backend.
codegraph CLAUDE.md
Instructions for Lordymine/codegraph, covering claude.md — codegraph, o que é, princípios de design (não violar sem motivo), estado atual — m0–m5 fechados and build & uso.
cli-printing-press CLAUDE.md
Claude Code instructions for mvanhorn/cli-printing-press, a project described as: Every API has a secret identity. This finds it, absorbs every feature from every competing tool, then builds the GOAT CLI — designed for AI agents first, with SQLite sync, offline search, and compound insight commands.