Borrowing it
Nothing to install: this file belongs to joseikininsight-hue/sales-claw-ts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/joseikininsight-hue/sales-claw-ts/main/CLAUDE.mdgit clone --depth 1 https://github.com/joseikininsight-hue/sales-claw-tsWrote 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/joseikininsight-hue/sales-claw-ts/claude-md)<a href="https://agentmods.dev/instructions/joseikininsight-hue/sales-claw-ts/claude-md"><img src="https://agentmods.dev/badge/instructions/joseikininsight-hue/sales-claw-ts/claude-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.
<a href="https://agentmods.dev/instructions/joseikininsight-hue/sales-claw-ts/claude-md"><img src="https://agentmods.dev/badge/instructions/joseikininsight-hue/sales-claw-ts/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.10562 | $0.10562 |
| Opus 5.5 | $0.04225 | $0.04225 |
| Sonnet 5.5 | $0.02112 | $0.02112 |
| Haiku 4.5 | $0.01056 | $0.01056 |
Grade A, and why
sales-claw-ts CLAUDE.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 27d 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.
- Record a `skipped` action via `curl POST /api/log-action` (details in the How it starts
The opening of the file, as written. The whole thing — 921 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sales Claw
Japanese version: docs/ja/CLAUDE.md
About This Project
A tool that automates B2B outreach through company contact forms. Based on the user's company profile, target list, and value propositions configured in settings, the Claude Code CLI performs: company analysis → message generation → form filling.
ABSOLUTE RULE: Never log awaiting_approval without form-fill + screenshot
This is the single most important rule in this project. Violations are not acceptable.
Before logging an awaiting_approval action, you MUST complete every one
of the following steps:
- Open the form URL — use the MCP Playwright
browser_navigate/browser_tabstools to open the official site / contact page. - Parse the form structure — use MCP Playwright
browser_snapshotto identify each field. - Actually fill every field — use MCP Playwright
browser_fill_form/browser_type/browser_select_optionto enter company name, contact name, email, phone, and message body. - Take a screenshot of the filled form — use MCP Playwright
browser_take_screenshotand save toscreenshots/ss-{No}-input.png. - Log in order:
form_fill→confirm_reached→awaiting_approval.- The
detailspayload forawaiting_approval/submittedMUST includesentMessage(the exact text that was typed into the form body). Pass the actual string you typed into the contact form's body field, not the Phase AtemplateDraft. - From 1.2.100 onwards an API guard rejects requests with 422 if
sentMessageis missing or shorter than 30 characters; the log entry will not be recorded.
- The
Forbidden actions
- Logging
awaiting_approvalafter only generating a message (without touching the form). - Writing a
form_filllog entry without ever opening the form. - Going to
awaiting_approvalwithout taking a screenshot. - Silently going to
awaiting_approvalafter "couldn't find the form" → must be anerrorlog entry with the reason explicitly stated. - Omitting
sentMessagefrom thedetailsofawaiting_approval/submitted(this causes the dashboard view to diverge from what was actually typed — a real-world incident root cause). - Typing a degenerate body that is just a contact-info dump (TEL / MAIL
only) — the body must use
companyProfile.companyName+valuePropositions.strengths. Follow the output ofbuildMessagePrompt(analysis).
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.
- 27d ago Changed · +7 tokens per session f940d301dc2f
- 1mo ago First seen · 921 lines · 10,555 tokens per session scan A 35e6f5361cc4
sales-claw-ts CLAUDE.md is an instructions file published in the GitHub repository joseikininsight-hue/sales-claw-ts (7 stars, last pushed 28d ago), licensed MIT. It adds 10,562 tokens to every session, about $0.0422 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 2026-08-31.
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).
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.
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).
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.
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.