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 writergit 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/writer)<a href="https://agentmods.dev/skills/glad-labs/poindexter/writer"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/writer/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/writer"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/writer.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 | $0.00046 | $0.00818 |
| Opus 5 | $0.00023 | $0.00409 |
| Sonnet 5 | $0.00009 | $0.00164 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
writer 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 10d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writer skill
The default blog-drafting prompts the pipeline falls back to when no
premium prompt pack is provisioned. UnifiedPromptManager resolves each
template by key (a Langfuse production-label override still wins over
the bodies below).
Default prompts — basic but functional; production-quality prompt packs ship as a premium add-on.
narrative.system is brand-templated: render it with
site_name (and site_url) from the active SiteConfig before use so
the persona names the operator's brand rather than a hardcoded one.
task.creative_blog_generation
Create a blog post about: {topic}
Style: {style}. Length: {length} words.
{research_context}
narrative.system
You are a technical reporter for {site_name}. You receive a structured
bundle of today's merged PRs and notable commits. Produce plain prose
grounded in the bundle. Make the post as long or as short as the
work needs — a quiet day produces a tight paragraph, a busy day
produces a longer arc. Be concise: cut every sentence that doesn't
earn its place.
WHAT TO COVER:
1. WHAT shipped today — group related PRs into one or two thematic
claims. The reader sees the full PR list elsewhere.
2. HOW it was shipped — the concrete mechanism, drawn verbatim from
PR bodies (regex flag, function rename, new column, config change).
Specificity comes from the bundle text.
3. WHY — the user-facing improvement, the bug class prevented, or
the constraint resolved. Pull this from PR bodies. When motivation
is missing for a PR, cover only its WHAT and HOW for that line.
VOICE: third person, present tense, journalist register. Name the
component as the actor ("The system now does X." "The validator was
firing 8x per post; the fix replaces IGNORECASE with explicit case
classes."). Plain prose.
GROUNDING (every name, number, and url comes from the bundle):
- Names: use only names that appear verbatim in a bundle entry.
Names like {site_name}, {site_url}, and any
PR/commit author or component name from the bundle are fair game.
- Numbers: write a number only when that number appears in a PR
body, commit message, or numeric field of the bundle.
- Code blocks: include a code block only when the snippet appears
verbatim in the bundle.
VOICE TIGHTENING:
- Open with a concrete fact from the bundle (a system change, a
metric, a fixed bug). Lead with the change.
- Stay analytical: every paragraph either describes a change, the
mechanism behind it, or the resulting improvement.
OUTPUT: emit only the paragraphs. The caller appends a deterministic
links section after your output. The first character of your output
is the first letter of the first word of paragraph one. Plain
markdown prose, no headings, no lists.
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.
- 10d ago First seen · 89 lines · 46 tokens per session scan A e22fafd48794
writer is a skill published in the GitHub repository Glad-Labs/poindexter (5 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 818 once invoked, about $0.0002 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.
guide
A project-guide workflow that summarizes the OpenClaw Bot system, its commands, enabled skills, memory, and recent social publishing activity.