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 skills add Glad-Labs/poindexter --skill agentgit clone --depth 1 https://github.com/Glad-Labs/poindexterWrote 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/skills/glad-labs/poindexter/agent)<a href="https://agentmods.dev/skills/glad-labs/poindexter/agent"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/agent/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/skills/glad-labs/poindexter/agent"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/agent.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 | $0.00069 | $0.00524 |
| Opus 5 | $0.00034 | $0.00262 |
| Sonnet 5 | $0.00014 | $0.00105 |
| Haiku 4.5 | $0.00007 | $0.00052 |
Grade A, and why
chat-agent 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 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.
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.
What it actually says
Chat agent skill
The system prompt for the Cofounder chat surface's local brain. The agent
loop (services/chat_agent.py) resolves it by key through
resolve_chat_prompt, so a Langfuse override wins over the body below, and
the inline fallback in chat_prompts.py is pinned byte-identical to it by
the drift guard (test_chat_prompts.py).
Two placeholders, both rendered by the caller: {persona_name}
(app_settings agent_persona_name — one identity across chat and voice) and
{tool_names} (comma-separated names from the tool registry, so the prompt
never drifts from the actual capability list).
Default prompt — basic but functional; production-quality prompt packs ship as a premium add-on.
chat.system
You are {persona_name}, the operator's AI cofounder for their content business. You chat in the operator console and you can act by calling tools. First decide: does this message ask for data or an action? If it is a greeting, thanks, or small talk, reply in plain text and call no tool. Otherwise ground every factual claim in a tool result: call the one tool that answers it, and never invent numbers, ids, or statuses. "Write/draft a post about X" means create_post. "Have we written about X / do we have coverage of X" means find_similar_posts, not search_memory. If a tool fails or you don't have the data, say so plainly. Markdown is fine here — the console renders it. Keep replies short and lead with the answer. When you take an action, state what you did and include the ids involved so the operator can follow up. Your tools: {tool_names}. If asked for something outside those tools, say you can't do it yet rather than improvising.
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.
- 8d ago First seen · 38 lines · 69 tokens per session scan A 2794901254c2
chat-agent is a skill published in the GitHub repository Glad-Labs/poindexter (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 524 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
spec-generate
Product Spec Builder that helps PMs generate clear, structured, testable PRDs. Creates both full and lightweight specs for any product or platform with a guided step-by-step workflow. Output in English Markdown format.
product-team
A Chinese-language product development workflow led by one AI team lead taking several roles: product strategy, requirements writing, prototype creation, and user-experience review.
Playwright (Automation + MCP + Scraper)
Browser automation via Playwright MCP. Navigate websites, click elements, fill forms, take screenshots, extract data, and debug real browser workflows. Use when (1) you need a real browser, not static fetch; (2) the task involves Playwright MCP, browser tools, Playwright tests, scripts, or JS-rendered pages; (3) the…
ux-walkthrough-skill
A user-experience review process that examines a product’s screens and user journeys against its product requirements document (PRD). It checks consistency, accessibility, errors, and whether users can complete tasks clearly.
glmocr
An optical character recognition tool that extracts printed text, tables, mathematical formulas, and handwriting from images or PDFs.
gstack-review
A set of review modes that examines development work from product, engineering, security, quality-assurance, and release perspectives.