What is borderlint AGENTS.md?

A repository rulebook for building software from written specifications. It requires each change to be described, planned, and broken into tasks before code is written.

Use it to capture requirements, create task lists, prepare proposals, and guide agents through a fixed development workflow.

It prevents coding from starting with unclear requirements and keeps work traceable from the original request through to the final change.

How iolairus/borderlint configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to iolairus/borderlint. 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/iolairus/borderlint/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/iolairus/borderlint

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/iolairus/borderlint/agents-md/github.svg)](https://agentmods.dev/instructions/iolairus/borderlint/agents-md)

Your own site

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

Per session 1,689 This file is loaded in full into every session.

When invoked 1,689 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	$0.01689	$0.01689
Opus 5.5	$0.00676	$0.00676
Sonnet 5.5	$0.00338	$0.00338
Haiku 4.5	$0.00169	$0.00169

Measured 2mo ago against content hash cf3fdd815ed0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

borderlint 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 2mo 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions — Spec-Driven Development with OpenSpec

This repository follows spec-driven development: no code is written until the change is captured as an OpenSpec proposal with specs, design, and tasks. OpenSpec is the machinery that enforces this; opencode is the agent that executes it.

The golden rule

Spec → Plan → Code. Never skip a stage.

If a request arrives as "build X" and there is no OpenSpec change for it, your first move is /opsx:propose — not writing code.

Workflow

The full pipeline runs from requirements to merge. Stages 0–1 are optional for trivial changes; stages 2–6 are mandatory.

Discover — /req-capture <topic> interviews the user and writes backlog/discovery/<topic>.md. No invented answers: unknowns go to Open questions.
Tasks — /task-generate <topic> slices the discovery into tasks under backlog/tasks/. Alternative entries: /task-import <key> normalizes an existing Jira ticket (pasted by the user) into the backlog; /task-new <title> creates a single task without a discovery doc. Task IDs ARE Jira keys (<project_key>-<n>, provided by the user; -Dnn drafts until the issue exists). /task-enrich <id> adds edge cases, estimates, and unhappy paths; /review-task <id> audits; /task-jira <id> exports Jira wiki markup to backlog/exports/jira/ (not needed for imported tickets).
Propose — /opsx:propose <change-name> creates openspec/changes/<name>/ with proposal, delta specs, design, and tasks. If the change implements a backlog task, the proposal references its ID and the task frontmatter gets change: <name>.
Specify & plan — Delta specs (requirements + GIVEN/WHEN/THEN) as ADDED/MODIFIED/REMOVED; design.md for the approach; tasks.md for checkable steps.
Review — /review-change <name> audits the change before implementation.
Implement — /opsx:apply. Branch gate (mandatory, BEFORE writing any code): check the current branch first. Never implement on main. With work_mode: feature, create and switch to the feature branch (naming rule below) before touching any file. With work_mode: flexible, ask the user where to implement — feature branch (recommended) or directly on the integration branch — and create/switch accordingly before the first edit. Then commit with /git-commit: conventional commits whose footer traces Change:/Task: (tasks.md step)/Jira: (backlog task id).
Deliver — feature branch: /pr-open creates the PR against the integration branch, /ship validates, archives, merges and closes the backlog task. Integration branch: skip /pr-open; /ship validates, archives and pushes (no PR, no review).

Read the full file on GitHub · 66 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.

2mo ago First seen · 66 lines · 1,689 tokens per session scan A cf3fdd815ed0

Subscribe to this mod's changes

borderlint AGENTS.md is an instructions file published in the GitHub repository iolairus/borderlint (10 stars, last pushed 7d ago), licensed MIT. It adds 1,689 tokens to every session, about $0.0068 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 2026-08-31.

borderlint AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
borderlint AGENTS.mdiolairus/borderlint	Instructions file	10	7d ago	MIT	A	1,689	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	yesterday	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

borderlint: Instructions file for Codex