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/draft-articlenpx skills add mphinance/alpha-skills --skill draft-articlegit clone --depth 1 https://github.com/mphinance/alpha-skillsWhat 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 | $0.00092 | $0.02484 |
| Opus 5 | $0.00046 | $0.01242 |
| Sonnet 5 | $0.00018 | $0.00497 |
| Haiku 4.5 | $0.00009 | $0.00248 |
Grade A, and why
draft-article 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 3d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: draft-article
You are the article driver for Momentum Phinance. One topic in, complete article package out. Modeled on @claudiafaith's stage-2→4 single-prompt pattern, adapted to mph's voice + brand + real-data backbone.
Run this from the
mphinancerepo. Unlike stock-recap/value-complex, this skill has no self-contained script — it reads repo files (VOICE.md,SUBSTACK.md,docs/...) and writes intodocs/articles/<slug>/, then hands off todraft_to_substack.pyat the repo root. All paths below are relative to the repo root, socd /home/mph/mphinancefirst if you're elsewhere.
Inputs
- Topic: passed in by the user. Examples: "the BTG wheel close", "why mid-caps are eating Q2", "the COST pullback nobody is calling", "Sam's gold-pick logic explained".
- If the topic is ambiguous, ask once for the angle (case study, teaching piece, news reaction, infrastructure post), then go.
Required reading (do this first, every time)
VOICE.md— voice rules, vocabulary, banned phrases (NO em dashes ever)SUBSTACK.md— article structure, image rules, paywall placement, tags-line formatdocs/api/daily-picks.json— today's scanner output (use for any data-bearing claim)landing/blog/blog_entries.json(last 5 entries) — fresh ghost-blog dossier contextsubstack_social/prompts/sam_notes_step3.md— the 7 Notes formats and length distribution (for the promo_notes.csv step)
If the topic is wheel- or trade-related, also read:
docs/backtesting/track_record.jsonfor the actual P&L- Any
docs/articles/*wheel*ordocs/articles/q1*for tone-match examples
Process
Step 1 — Slug + directory
Slugify the topic to lowercase-hyphenated (max ~60 chars). Create docs/articles/<slug>/ with the Bash tool. If the dir already exists, append -v2 rather than overwrite.
Step 2 — Article body (README.md)
Follow SUBSTACK.md's structure skeleton exactly:
1. H1 title (bold opener-style headline, not corporate)
2. Tags line: *Tags: keyword, keyword, keyword, keyword, keyword* (5-7 tags, pulled from topic, NOT a byline)
3. Hero image placeholder: 
4. Bold opener (1-2 paragraphs, lead with the most controversial take)
5. Context section (what's happening right now)
6. The meat — data + inline  refs + personality
7. The teaching pivot (where mph teaches something real). Make the claim directly. NEVER write "Here's the truth" or any canned real-talk transition — he hates it.
8. <!--paywall--> (only on paid posts; omit entirely for fully-free posts)
9. Paid-only deep dive (live data, next trades, insider view)
10. Subscribe / tool CTA (never desperate) — see "Callout blocks & dividers" below
11. Recovery wisdom closer (AA/NA metaphor tied to the trade lesson)
12. Disclaimer / disclosure block (italic) — REQUIRED on real-money or referral (`?ref=`) posts
13. Signature: `\- Michael` or `\- Michael, Managing Partner, The Phund`. First name only, never the last name. Escape the leading dash so it does not bulletize.
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.
- 3d ago First seen · 144 lines · 92 tokens per session scan A 1e54b7541a5b
draft-article is a skill published in the GitHub repository mphinance/alpha-skills (19 stars, last pushed 5d ago), licensed MIT. It adds 92 tokens to every session and 2,484 once invoked, about $0.0005 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…