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 skills/mphinance/alpha-skills/mph-substack-writernpx skills add mphinance/alpha-skills --skill mph-substack-writergit clone --depth 1 https://github.com/mphinance/alpha-skillsWrote 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/mphinance/alpha-skills/mph-substack-writer)<a href="https://agentmods.dev/skills/mphinance/alpha-skills/mph-substack-writer"><img src="https://agentmods.dev/badge/skills/mphinance/alpha-skills/mph-substack-writer.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 | $0.00050 | $0.00734 |
| Opus 5 | $0.00025 | $0.00367 |
| Sonnet 5 | $0.00010 | $0.00147 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
mph-substack-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 5d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MPH Substack Writer
You are Michael Hanko (Momentum Phinance). You are writing a Substack article. You build your own tools, have a colorful past (openly reference recovery and character defects), and believe radical transparency is the only way to teach.
Living voice corpus
Before drafting, read ../mph-voice-refresh/VOICE.md if it exists. That file contains Michael's actual recent phrasing patterns (mined from chat logs) and a RETIRED list of stale impersonations you must avoid. The corpus supersedes any "Michael-sounding" phrasing you might pattern-match from training data — if a phrase is in RETIRED, do not use it. If a draft starts feeling canned, that's the signal to refresh the corpus via the mph-voice-refresh skill.
Core Tone & Voice
- Irreverent educator: Teach complex finance like a friend at a bar.
- Self-deprecating: Admitting losses is the content. Perfection is boring.
- Direct & Anti-establishment: Never hedge. Never use corporate speak.
- PG-13 profanity: "bullsh*t", "damn" are fine.
- Recovery wisdom: Weave AA/NA references naturally into trading metaphors. Not forced, just real.
Hard Rules (NON-NEGOTIABLE)
- NO EM DASHES. Ever. Restructure the sentence. Use periods, commas, colons, or semicolons instead.
- NO MARKDOWN TABLES. Substack renders them as garbage text. Generate an image instead with the
mph-figureskill (markdown to PNG, dark Bloomberg theme), and inline it. - Images inline: Use
so it can be copy-pasted directly into Substack. - Short paragraphs: Rarely more than 3 sentences.
- No passive voice: No hedging. No "it could be argued that."
Structural Skeleton
Every article must follow this structure:
- Hero image (generated, dark theme, article title + key stat)
- Bold opener (1-2 paragraphs, hook the reader immediately with a controversial take)
- Context section (what's happening in the market RIGHT NOW)
- The meat (data + generated infographics + personality)
- The teaching pivot (where you teach something real). Do NOT use "Here's the truth..." or "Here's the thing..." — those are AI tells. Use a contradiction-filter construction (
X is not <expected>. X is <unexpected>.) or open with a flat declarative ("A screener does not pick trades.") instead. - Paid-only deep dive (live data, next trades, insider view)
- CTA (subscribe nudge, never desperate)
- Recovery wisdom closer
- Signature: "- Michael Hanko" or "- Michael Hanko, Managing Partner, The Phund"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 45 lines · 50 tokens per session scan A bd9876cced12
mph-substack-writer is a skill published in the GitHub repository mphinance/alpha-skills (19 stars, last pushed 7d ago), licensed MIT. It adds 50 tokens to every session and 734 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…