herdr-file-annotator AGENTS.md

Review instructions for herdr-file-annotator, focused on checking code changes against that repository's business rules and review standards.

In plain words
What is it for?
Use them when reviewing a pull request, diff, or other proposed change in the repository.
Why use it?
They prevent reviews from relying only on a short instruction file when the full rules are in REVIEWS.md.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/jonasbaeumer/herdr-file-annotator/agents-md
Clone the repo
git clone --depth 1 https://github.com/JonasBaeumer/herdr-file-annotator

Made for: Codex, OpenCode.

Per session 110 This file is loaded in full into every session.
When invoked 110 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00110 $0.00110
Opus 5 $0.00055 $0.00055
Sonnet 5 $0.00022 $0.00022
Haiku 4.5 $0.00011 $0.00011

Measured 3d ago against content hash 53f86be7601e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

herdr-file-annotator 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 3d 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.

AGENTS.md · 12 lines

What it actually says

AGENTS.md

Reviewing a diff in this repo

Read REVIEWS.md before reviewing. It carries the full review guidelines: how to derive and confirm the business rule a diff asserts, the P0 and P1 severity lists, the Rust and tooling rules specific to this repo, and the recurring domain ambiguities to ask about.

This applies to any review task — a pull request, a diff handed over by an agent, or a pre-merge check. Do not review from this file alone.

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.

  1. 3d ago First seen · 12 lines · 110 tokens per session scan A 53f86be7601e

Subscribe to this mod's changes

herdr-file-annotator AGENTS.md is an instructions file published in the GitHub repository JonasBaeumer/herdr-file-annotator (41 stars, last pushed 3d ago), licensed MIT. It adds 110 tokens to every session, about $0.0006 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.

Related

Other instructions, from other repositories

crabbox AGENTS.md

Instructions for openclaw/crabbox, covering repository guidelines, project structure & module organization, product positioning, architecture boundaries and build, test, and development commands.

openclaw/crabbox · 1,336 tokens

collie CLAUDE.md

Instructions for AltanS/collie, covering claude.md — working agreement for this repo, decision records — read before reopening a settled question, versioning — mandatory, build / run (operational facts that are easy to forget) and frontend data layer (react router, not tanstack).

AltanS/collie · 4,592 tokens

collie AGENTS.md

Instructions for AltanS/collie: The working agreement for this repo lives in CLAUDE.md — read it before changing anything. This file exists so agents that look for AGENTS.md find it too; there is one set of rules, not two, so nothing is restated here.

AltanS/collie · 74 tokens

herdr-agent-usage AGENTS.md

Instructions for senna-lang/herdr-agent-usage, covering project instructions, scope, provider extensibility, provider symmetry and directory and package boundaries.

senna-lang/herdr-agent-usage · 784 tokens

herdr-plugin-renamer CLAUDE.md

Instructions for wyattjoh/herdr-plugin-renamer, covering claude.md, architecture, naming engines, module map and conventions.

wyattjoh/herdr-plugin-renamer · 3,031 tokens

sheep AGENTS.md

Instructions for gokay-ai/sheep, covering agents.md, build, test, check, always set sheepstatedir when you run the binary by hand, the safety invariants and where things are.

gokay-ai/sheep · 5,189 tokens