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/maguro/pbf/agents-mdgit clone --depth 1 https://github.com/maguro/pbfWhat 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 | $0.00462 | $0.00462 |
| Opus 5 | $0.00231 | $0.00231 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
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 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.
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 — 52 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. - If
AGENTS.mdandCODING_STANDARDS.mddiffer, follow the stricter rule.
Project Overview
- Language: Go
- Module:
m4o.io/pbf/v2 - Primary goals: stable PBF encoder/decoder library and
pbfCLI
Environment
- Preferred Go version:
1.23.x(seego.modtoolchain) - OS support: macOS, Linux, Windows
Working Agreement
- Keep edits minimal and targeted to the task.
- Preserve public API behavior unless change is explicitly requested.
- Prefer table-driven tests for new behavior.
- Avoid introducing new dependencies without clear need.
Analysis Depth
- When collaboration level is
HighorExtra High, perform deep analysis before editing. - Do not stop at first-order reasoning; check invariants, race/close paths, and edge cases.
- State assumptions explicitly and verify them against code before implementation.
Fast Start
- Format:
make fmt - Unit tests:
make test - Race tests:
make test-race - Integration tests:
make test-integration - Lint:
make lint - Full local CI parity:
make verify
Code Style
- Follow standard
gofmtformatting. - Keep package boundaries explicit (
internal/remains non-public). - Return wrapped errors when adding new error paths (
fmt.Errorf("...: %w", err)).
Validation Before Merge
- Run
make verify. - If behavior changes, add or update tests in the same change.
- Keep README/docs in sync with user-facing CLI/library changes.
Execution Defaults
- Make one focused change at a time and stop for review.
- Do not bundle unrelated edits in a single change.
- Do not use staging/cherry-pick style split workflows unless explicitly requested.
- Preserve behavior unless an explicit behavior change is approved.
- For concurrent close/error paths, default to first-wins semantics unless explicitly changed.
- When refactoring a proposed solution, re-scan pending changes and remove code that is no longer relevant.
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 · 52 lines · 462 tokens per session scan A 308d0ea92c74
pbf AGENTS.md is an instructions file published in the GitHub repository maguro/pbf (56 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 462 tokens to every session, about $0.0023 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
no-mistakes AGENTS.md
AGENTS.md instructions for kunchenguid/no-mistakes, covering agents.md and maintaining this file.
trpc-agent-go AGENTS.md
AGENTS.md instructions for trpc-group/trpc-agent-go, covering agents.md, project overview, engineering principles, go design conventions and implementation workflow.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
stackql AGENTS.md
Instructions for stackql/stackql, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
goai AGENTS.md
Instructions for zendev-sh/goai, covering agents.md - goai, commands, architecture, key rules and adding providers.
unraid-management-agent copilot-instructions.md
Instructions for ruaan-deysel/unraid-management-agent, covering copilot instructions, copilot workflow, path-specific instructions, reusable prompts and quick commands.