Borrowing it
Nothing to install: this file belongs to spirosbax/insaight. 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/spirosbax/insaight/main/CLAUDE.mdgit clone --depth 1 https://github.com/spirosbax/insaightWrote 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/spirosbax/insaight/claude-md)<a href="https://agentmods.dev/instructions/spirosbax/insaight/claude-md"><img src="https://agentmods.dev/badge/instructions/spirosbax/insaight/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/spirosbax/insaight/claude-md"><img src="https://agentmods.dev/badge/instructions/spirosbax/insaight/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 | $0.02432 | $0.02432 |
| Opus 5.5 | $0.00973 | $0.00973 |
| Sonnet 5.5 | $0.00486 | $0.00486 |
| Haiku 4.5 | $0.00243 | $0.00243 |
Grade A, and why
insaight 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 4d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Insaight — LinkedIn Intelligence Tool
Scrapes LinkedIn company pages and personal profiles via Apify, stores in SQLite, and exposes them to Claude via MCP for prospect research and cold outreach.
Skills live in skills/<name>/SKILL.md — each is independently invocable and they chain
conversationally (research → outreach → save).
Setup
User config lives in ~/.insaight/config.md (created by get_config() on
first call) — not in this file. The block below is the template; skills
call insaight:get_config to read it.
NOTION_WORKSPACE: YourWorkspaceName # your Notion workspace / team name
NOTION_RESEARCH_PAGE: Prospect Research # parent page for research briefs
NOTION_OUTREACH_LOG: Sent Log # your sent-messages archive (READ-ONLY)
COMPANY_NAME: YourCompany # your company (used by draft-post)
COMPANY_LINKEDIN: your-company-slug # your LinkedIn company page slug
Insaight MCP — Tool Reference
All tools must be loaded first via tool_search(query="insaight").
| Tool | Purpose | Key params |
|---|---|---|
insaight:list_accounts |
Show all tracked accounts + slugs | — |
insaight:get_stats |
DB-wide overview (counts, date range, categories) | — |
insaight:list_posts |
Slim index: metadata + 150-char snippet, NO full text | account, days_ago, limit, min_engagement |
insaight:search_posts |
Full-text keyword search → returns full content | query, account, days_ago, limit |
insaight:get_posts |
Fetch full content for specific URNs (max 20) | urns: string[] |
insaight:scrape_profile |
Scrape fresh posts from any LinkedIn URL via Apify | url, max_posts |
insaight:list_people |
List stored employees/leadership from DB (instant) | account, role, limit |
insaight:scrape_people |
Scrape + store company leadership via Apify | url, job_titles, max_items, full_mode |
insaight:scrape_person_profile |
Enrich ONE person with full profile (experience, education, skills, etc.) | url, with_email, company_url |
insaight:scrape_post_comments |
Scrape comments on a LinkedIn post (with replies + author info) | post_url, max_items, include_replies, profile_mode |
insaight:list_comments |
List stored comments for a post, ranked by likes | post_urn or post_url, limit, min_likes, include_replies |
insaight:log_outreach |
Record a SENT message in the ledger (flags prior contact) | target_url, message, target_name, channel, variant, hook_type |
insaight:record_outcome |
Record replied/positive/meeting/ghosted; flags when reflection is due | outreach_id or target_url, outcome, reply_snippet |
insaight:list_outreach |
Query the outreach ledger (prior-contact checks, pending review) | outcome, target, limit, full |
insaight:get_outreach_stats |
Reply-rate breakdown by hook/variant/channel + reflection state | — |
insaight:get_memory |
Read distilled style + playbook memory (draft skills read THIS) | — |
insaight:update_memory |
Rewrite a memory file — only after user approval | kind, content, mark_reflection_done |
insaight:get_config |
User config: Notion pages + company name/slug (~/.insaight/config.md) |
— |
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.
- 4d ago First seen · 184 lines · 2,432 tokens per session scan A 8271ec0e9c43
insaight CLAUDE.md is an instructions file published in the GitHub repository spirosbax/insaight (32 stars, last pushed 10d ago), licensed MIT. It adds 2,432 tokens to every session, about $0.0097 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 2026-10-14.
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.