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/gregmos/memoforge/stylenpx skills add gregmos/memoforge --skill stylegit clone --depth 1 https://github.com/gregmos/memoforgeWhat 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 | $0.00038 | $0.03258 |
| Opus 5 | $0.00019 | $0.01629 |
| Sonnet 5 | $0.00008 | $0.00652 |
| Haiku 4.5 | $0.00004 | $0.00326 |
Grade A, and why
style 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 2d 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memoforge / style skill
You manage the user's custom style profiles. A profile is a directory under ~/.claude/plugin-data/memoforge/profiles/<name>/ containing prose-style.md (always), template.md (sometimes), meta.json, and supporting files. The memo skill reads these at Phase 1.5 when the user picks a profile for a new memo.
Authority hierarchy (highest wins, same shape as memo skill):
- Cowork / Anthropic platform policy.
- This skill and its arguments.
scripts/resolve_style_profile.py— the canonical write path for profiles. Never bypass it.- User input from
AskUserQuestionor text replies.
Key invariant. All user-facing strings (menu items, checkpoint questions, warnings, summaries) are English. The contents of generated prose-style.md and template.md are in the input language (English, Russian, etc.) — that is the extractor's concern, not yours.
Parse $ARGUMENTS
Split $ARGUMENTS by whitespace. The first token is the action:
new <name> [flags…]— create a new profile. See §newbelow.list— list existing profiles. See §list.use <name>oruse --clear— set or clear the default profile. See §use.show <name>— print profile contents. See §show.delete <name>— delete a profile. See §delete.- (no action / empty
$ARGUMENTS/menu/help) — go to §menu(interactive).
For any other first token, print: Unknown action. Use new | list | use | show | delete, or run /memoforge:style with no arguments for the interactive menu. End turn.
menu — interactive entry point
When $ARGUMENTS is empty, ask the user what they want to do. Use AskUserQuestion with these options (English; copy verbatim):
- Question: "What would you like to do?"
- Header: "Style" (≤12 chars).
- multiSelect: false.
- Options:
- label: "Create a new profile", description: "From example memos, written rules, or both"
- label: "List existing profiles", description: "See your saved profiles, current default, mode bindings"
- label: "Set default profile", description: "Choose which profile /memo uses by default"
- label: "Show profile contents", description: "Print prose-style.md and template.md of a profile"
- label: "Delete a profile", description: "Remove a profile permanently"
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.
- 2d ago First seen · 313 lines · 38 tokens per session scan A 1e89409545f3
style is a skill published in the GitHub repository gregmos/memoforge (20 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 3,258 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…