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/s87343472/backlink-pilot/claude-mdgit clone --depth 1 https://github.com/s87343472/backlink-pilotWrote 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.
[](https://agentmods.dev/instructions/s87343472/backlink-pilot/claude-md)<a href="https://agentmods.dev/instructions/s87343472/backlink-pilot/claude-md"><img src="https://agentmods.dev/badge/instructions/s87343472/backlink-pilot/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01419 | $0.01419 |
| Opus 5 | $0.00709 | $0.00709 |
| Sonnet 5 | $0.00284 | $0.00284 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
backlink-pilot CLAUDE.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 6d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlink Pilot v2.1 — Claude Code Instructions
Returning session? Read
.claude-local.mdfirst for project history and context.
You are operating backlink-pilot v2.1, an automated backlink submission toolkit. Your job: help users submit their product to directory sites with minimal effort.
First-time User Flow
When a user opens this project for the first time, guide them step by step:
Step 1: Check prerequisites
node --version # Need 18+
bb-browser --version # Need 0.10+, install: npm install -g bb-browser
If bb-browser is missing, install it:
npm install -g bb-browser
Step 2: Create config.yaml
Ask the user these questions (and ONLY these — keep it simple):
- Product name? (e.g. "Metric Converter")
- Product URL? (e.g. "https://metric-converter.net")
- One-line description? (under 160 chars)
- Longer description? (2-3 sentences about features and audience)
- Contact email?
Then generate config.yaml from config.example.yaml with their answers. Set browser.engine: bb.
Step 3: Start Chrome
bb-browser open about:blank
If this times out or errors, guide user to:
# Kill any stuck Chrome
pkill -f "bb-browser" || true
# Retry
bb-browser open about:blank
Step 4: Submit
Start with ONE site to verify everything works:
node src/cli.js submit futuretools --engine bb
Available Commands
| Command | What it does |
|---|---|
node src/cli.js submit <site> |
Submit to a known site adapter |
node src/cli.js submit <url> |
Generic submission to any directory URL |
node src/cli.js scout <url> --deep |
Discover form fields on a new site |
node src/cli.js awesome <repo> |
Generate awesome-list GitHub Issue body |
node src/cli.js indexnow <url> |
Ping Bing/Yandex about new pages |
node src/cli.js status |
Show submission history |
node src/cli.js bb-update |
Update bb-browser community adapters |
node src/batch-submit.js --limit N |
Batch blog comment submissions |
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.
- 6d ago First seen · 150 lines · 1,419 tokens per session scan A 1281d574372f
backlink-pilot CLAUDE.md is an instructions file published in the GitHub repository s87343472/backlink-pilot (354 stars, last pushed 5mo ago), licensed MIT. It adds 1,419 tokens to every session, about $0.0071 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
rankgoat-cli CLAUDE.md
Claude Code instructions for madrzak/rankgoat-cli, covering claude.md - apps/cli, rules, shape and commands.
marketingskills AGENTS.md
AGENTS.md instructions for coreyhaines31/marketingskills, covering agents.md, repository overview, repository structure, build / lint / test commands and versioning.
aso-skills AGENTS.md
AGENTS.md instructions for Eronred/aso-skills, covering agent guidelines, structure, skill.md format, writing style and app store reference.
pruna-skills AGENTS.md
AGENTS.md instructions for PrunaAI/pruna-skills, covering pruna skills (agent notes), how it works, clarification (library-wide), install and layout.
marketingskills CLAUDE.md
Claude Code instructions for coreyhaines31/marketingskills, a project described as: Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.
redbeacon AGENTS.md
AGENTS.md instructions for jidouqie/redbeacon, covering redbeacon · agent 工作台说明（host 无关）, 架构（一句话）, 整条运作链路, 能力 → skill 路由（两端 skill 名已统一，全英文） and 给 agent 的硬规则.