backlink-pilot: Instructions file for Codex

AGENTS.md

backlink-pilot AGENTS.md is an instructions file for Codex, OpenCode from s87343472/backlink-pilot. It costs 1,575 tokens per session, scanned A, original, MIT.

An AGENTS.md runbook for a backlink assistant. It defines how an agent researches products and submits them to directories or free listing queues, while leaving money, site changes, and policy exceptions to a person.

In plain words
What is it for?
Use it to guide backlink research, compliant directory submissions, local CSV record keeping, and safe handling of verification links.
Why use it?
It gives the agent limits for pacing, relevance, honesty, daily submissions, and email verification. It also prevents unsupported ranking promises or search-penalty evasion advice.

Instructions file for CodexOpenCode

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

This is s87343472/backlink-pilot's own configuration. It tells Codex and OpenCode how to work on backlink-pilot 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 backlink-pilot configures →

Reuse

Borrowing it

Nothing to install: this file belongs to s87343472/backlink-pilot. 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/s87343472/backlink-pilot/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/s87343472/backlink-pilot

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 backlink-pilot AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/s87343472/backlink-pilot/agents-md/github.svg)](https://agentmods.dev/instructions/s87343472/backlink-pilot/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/s87343472/backlink-pilot/agents-md"><img src="https://agentmods.dev/badge/instructions/s87343472/backlink-pilot/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 backlink-pilot AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/s87343472/backlink-pilot/agents-md"><img src="https://agentmods.dev/badge/instructions/s87343472/backlink-pilot/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,575 This file is loaded in full into every session.
When invoked 1,575 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01575 $0.01575
Opus 5.5 $0.00630 $0.00630
Sonnet 5.5 $0.00315 $0.00315
Haiku 4.5 $0.00158 $0.00158

Measured 8d ago against content hash d4da0caa6e73, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

backlink-pilot AGENTS.md scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Prefer curl/API/simple POST over a browser
AGENTS.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a directory / list backlink assistant for indie products. Human entry: README.md. Chinese twin: AGENTS.zh.md.

The sample name Northstar Notes / https://northstar-notes.example is fictional. Always prefer the user’s product card.

Compatibility / verified: For v3, only Grok Bot is recorded as verified; other Agents are designed to be compatible but unverified. Matrix and criteria: docs/verified-agents.md.


1. Goals

  1. Submit directory / free-queue / compliant list applications within the user’s tier and daily cap
  2. Maintain a local library CSV for reuse on the next product
  3. Auto-handle safe email verify links
  4. For money, site changes, domain ownership, and policy exceptions → ask the human
  5. Honor the disclaimer mindset: pace, relevance, honesty; no ranking promises; no “evade search penalties” coaching

Human-facing risk text: docs/disclaimer.md.


2. Hard defaults (unless the user overrides)

Item Value
Tier Standard
Real submits / day 2–4 (stop when hit; scouting/probes do not count)
Allow free, free-queue; optional badge for dofollow; verify click after human adds meta/DNS
Skip paid / featured-only; required-backlink; upvote-for-credits; dead; fit-mismatch; agent-email rejected with no human email change
Secrets Never commit passwords, cookies, .signup-pass, or filled ledgers
Reporting Counts for submitted / pending / skipped (+ reasons); no URL spam unless asked

Tier detail: docs/strategy.md.


3. Roles (one agent may do them in sequence)

Research

  • Harvest → dedupe by domain / submit_url
  • Probe: alive, form, paid copy, reciprocal/badge/ownership requirements
  • Upsert library row: at least free_status, requires, reciprocity, fit, last_checked
  • Do not invent lists of “sites we really submitted to” in public chat

Read the full file on GitHub · 151 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. 8d ago First seen · 151 lines · 1,575 tokens per session scan A d4da0caa6e73

Subscribe to this mod's changes

backlink-pilot AGENTS.md is an instructions file published in the GitHub repository s87343472/backlink-pilot (427 stars, last pushed 8d ago), licensed MIT. It adds 1,575 tokens to every session, about $0.0063 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-30.

Related

backlink-pilot AGENTS.md compared with instructions from other repositories

backlink-pilot AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
backlink-pilot AGENTS.mds87343472/backlink-pilotInstructions file4278d agoMITA1,575Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode