herdr-lantern: Instructions file for Codex

AGENTS.md

herdr-lantern AGENTS.md is an instructions file for Codex, OpenCode from aigorahub/herdr-lantern. It costs 638 tokens per session, scanned A, original, MIT.

Repository instructions for an AI coding agent working on the herdr-lantern project. They describe how to decide whether tests are worthwhile and how tests should check real behavior.

In plain words
What is it for?
Use them to guide bug fixes, cleanup, test selection, integration tests, end-to-end tests, and comments while modifying the project.
Why use it?
They reduce unnecessary tests and help catch bugs at important boundaries such as user input, files, requests, and model output.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is aigorahub/herdr-lantern's own configuration. It tells Codex and OpenCode how to work on herdr-lantern itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything herdr-lantern configures →

Reuse

Borrowing it

Nothing to install: this file belongs to aigorahub/herdr-lantern. 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/aigorahub/herdr-lantern/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/aigorahub/herdr-lantern

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.

agentmods badge for herdr-lantern AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aigorahub/herdr-lantern/agents-md/github.svg)](https://agentmods.dev/instructions/aigorahub/herdr-lantern/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/aigorahub/herdr-lantern/agents-md"><img src="https://agentmods.dev/badge/instructions/aigorahub/herdr-lantern/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.

agentmods 80×15 button for herdr-lantern AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/aigorahub/herdr-lantern/agents-md"><img src="https://agentmods.dev/badge/instructions/aigorahub/herdr-lantern/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 638 This file is loaded in full into every session.
When invoked 638 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00638 $0.00638
Opus 5.5 $0.00255 $0.00255
Sonnet 5.5 $0.00128 $0.00128
Haiku 4.5 $0.00064 $0.00064

Measured today against content hash f8bed7e6fcc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

herdr-lantern 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 today.

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 · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent rules

Done means the goal is met, not that nothing more can be found. In an authorized cleanup, when in doubt, delete, but keep a test that records a bug, a requirement, or an edge case.

Tests

  • Test only when an escaped bug costs more than keeping the test: money, data loss, security, runtime boundaries (model output, request bodies, files, user input), silent wrong answers. Skip cheap or obvious failures.
  • Use the fewest tests that catch real failures. Extend an existing test before adding one. Coverage is never a reason.
  • Use the cheapest reliable test at the boundary where the risk is. Add integration or end-to-end tests when wiring or rendering is the risk.
  • No tests for what the type system enforces, no tautologies (expected values computed by the code under test), no mocks of the system under test, no snapshot tests by default.
  • A test for a bug fix or behavior change must fail on the last revision without the change, because of the defect. Characterization tests may pass on both. If a test needs elaborate setup, simplify it or drop it.
  • Each test names the input or state that breaks things and asserts behavior at the boundary, not internals.
  • Never require an exact match of generated prose. Keep exact checks for deterministic contracts: schemas, required identifiers, tool arguments, limits. Define semantic tolerances before running, and never loosen them after a failure.
  • Never edit, skip, or weaken a test to make it pass. Claim a pass only for a run you saw, and name the commit.

Comments

  • Comment only why: a non-obvious reason, an invariant the types cannot express, an external constraint or workaround, an intentional edge case. Never restate the code. No filler.
  • Each comment is self-contained and stays true when nearby code changes.

Finishing work

  • A finding blocks only when it names a trigger, a code path, an impact, and evidence for one of these: data loss, a security hole, a wrong answer, a crash, a broken build, a destructive migration, or a missing acceptance criterion. Changed code can expose a defect in unchanged code. Speculative improvements are advisory and become issues.
  • Review each batch with two reviewers until it is green: one full review, then a delta review of every fix, until neither reviewer has a blocking finding. A delta review covers only the delta. Never merge a fix that no reviewer has seen.
  • If the two reviewers disagree, the user decides from the evidence. The final review uses all configured reviewers, under the same rules.
  • A docs-only commit needs no new review or full CI rerun.
  • Test infrastructure is not product scope. Green CI on the exact starting commit is the baseline. After a change, rerun the affected checks, including after dependency, config, fixture, or environment changes.
  • If a requirement is impossible as written, say so and propose an alternative. Never redefine acceptance silently.
  • At each batch end, report batches done against batches planned.

Read the full file on GitHub · 29 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.

  1. today First seen · 29 lines · 638 tokens per session scan A f8bed7e6fcc5

Subscribe to this mod's changes

herdr-lantern AGENTS.md is an instructions file published in the GitHub repository aigorahub/herdr-lantern (70 stars, last pushed today), licensed MIT. It adds 638 tokens to every session, about $0.0026 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 2026-10-30.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens