What is pbf AGENTS.md?

A repository guide for developers and coding agents working on pbf, a Go library and command-line tool for encoding and decoding Protocol Buffers, a data format for structured messages. It lists required documents, supported environments, working rules, and verification commands.

Checking required files before editing, keeping Go changes focused, writing table-driven tests, and running formatting, tests, race checks, integration tests, linting, or full verification.

It prevents changes that conflict with the project's standards, public behavior, supported systems, or required checks.

How maguro/pbf configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to maguro/pbf. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/maguro/pbf/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/maguro/pbf

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/maguro/pbf/agents-md/github.svg)](https://agentmods.dev/instructions/maguro/pbf/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/maguro/pbf/agents-md"><img src="https://agentmods.dev/badge/instructions/maguro/pbf/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/maguro/pbf/agents-md"><img src="https://agentmods.dev/badge/instructions/maguro/pbf/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 688 This file is loaded in full into every session.

When invoked 688 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00688	$0.00688
Opus 5.5	$0.00275	$0.00275
Sonnet 5.5	$0.00138	$0.00138
Haiku 4.5	$0.00069	$0.00069

Measured yesterday against content hash f2b7ecb29fe7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pbf 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.

AGENTS.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Required reads

Before making any code or test edits, read CODING_STANDARDS.md. It holds the rules that apply to every edit. If this file and CODING_STANDARDS.md differ, follow the stricter rule.

Skills

Use these skills from .claude/skills/ when the task matches:

Skill	Use it when
`go-testing`	Writing or changing a test
`go-benchmarks`	Changing a hot path listed below
`git-commit-message`	Writing a commit message
`asd-ste100`	Writing or checking a code comment or a commit body
`adr-writer`	Writing an ADR, or finishing one drafted by hand

.claude/workflows/ holds the adr-validate and adr-validate-lite workflows. They run a final adversarial review of an ADR in docs/adr/.

Design docs

docs/adr/ holds the design docs of this repo. Each design decision and its reasons go in an ADR there.

Project overview

Language: Go
Module: m4o.io/pbf/v2
Primary goals: stable PBF encoder/decoder library and pbf CLI
Preferred Go version: 1.25.x (see go.mod)
OS support: macOS, Linux, Windows

Commands

Format: make fmt
Format check: make check-fmt
Unit tests, with the race detector: make test
Integration tests: make test-integration
Benchmarks: make bench
Benchmark comparison: make bench-compare BASE=<commit> (default HEAD)
Coverage: make coverage
Fuzz: make fuzz FUZZ=<target> FUZZTIME=<duration>
Lint: make lint
Gate target: make check

Before each commit

Do all of these steps before each commit. Do not ask for permission to do them.

Run make fmt, make test, and make lint.
Use the asd-ste100 skill to check each comment that the change adds or changes. Also check the commit body.
Run /code-review against the diff, unless the change is trivial.
Use the go-benchmarks skill if the change touches a hot path that this file lists.
Run make check in the working tree.

Tell the user which steps you did and which steps you skipped. Give the reason for each skipped step.

Read the full file on GitHub · 81 lines

Changes

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 · +9 lines · +90 tokens per session f2b7ecb29fe7
2d ago Changed · +14 lines · +137 tokens per session 27df692f001a
5d ago Changed · -41 lines · -496 tokens per session 5e5ba44db738
8d ago Changed · +47 lines · +495 tokens per session 426cc4a1d1e6
2mo ago First seen · 52 lines · 462 tokens per session scan A 308d0ea92c74

Subscribe to this mod's changes

pbf AGENTS.md is an instructions file published in the GitHub repository maguro/pbf (57 stars, last pushed 2d ago), licensed Apache-2.0. It adds 688 tokens to every session, about $0.0028 per session on Opus 5.5. 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.

Go Languages openstreetmap openstreetmap-pbf openstreetmap-pbf-parser openstreetmap-protobuffer-format

pbf AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pbf AGENTS.mdmaguro/pbf	Instructions file	57	2d ago	Apache-2.0	A	688	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

pbf: Instructions file for Codex