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/memmachine/memmachine.github.io/write-blognpx skills add MemMachine/memmachine.github.io --skill write-bloggit clone --depth 1 https://github.com/MemMachine/memmachine.github.ioWhat 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 | $0.00040 | $0.01444 |
| Opus 5 | $0.00020 | $0.00722 |
| Sonnet 5 | $0.00008 | $0.00289 |
| Haiku 4.5 | $0.00004 | $0.00144 |
Grade C, and why
write-blog scanned grade C with 1 finding 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 yesterday.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Replace this comment with your blog post content. BEFORE PUBLISHING: 1. Confirm the date above is today or in the past — Hugo silently hides future-dated posts 2. Add featured_image.png to this directory (same folde How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/write-blog
Create a new blog post for the MemMachine website (memmachine.github.io) with the correct directory structure, complete YAML frontmatter, and build verification.
Usage
/write-blog # interactive — prompts for all fields
/write-blog "Post Title" # pre-fill the title, prompt for remaining fields
What You Must Do When Invoked
Follow these steps in order. Do not skip steps.
Step 1 — Collect post metadata
If any of the following are not provided in the invocation arguments, ask for them now (you may ask for all missing fields in a single message):
| Field | Required | Notes |
|---|---|---|
| title | Yes | Full post title (e.g., "MemMachine Now Supports LangGraph") |
| author | Yes | Author's full name as it should appear on the post |
| description | Yes | One sentence for SEO and social preview cards |
| tags | Yes | Comma-separated list (e.g., "AI Agent, Integration, LLM"). Always include at least one. |
| date | Yes | Publish date in YYYY-MM-DD format. Defaults to today if not provided. Must not be in the future — Hugo silently suppresses future-dated posts at build time unless --buildFuture is passed. If the post won't appear, check the date first. |
| featured | No | Should this post appear in the homepage carousel? (add tag "featured") |
Step 2 — Derive the slug and path
From the title:
- Lowercase the entire title.
- Replace spaces and any non-alphanumeric characters with hyphens.
- Collapse multiple consecutive hyphens into one.
- Strip leading and trailing hyphens.
From the date, extract YYYY and MM (zero-padded).
Construct the directory path:
content/en/blog/{YYYY}/{MM}/{slug}/
Example: title "MemMachine Joins NVIDIA NeMo Toolkit", date 2026-04-27:
- slug:
memmachine-joins-nvidia-nemo-toolkit - path:
content/en/blog/2026/04/memmachine-joins-nvidia-nemo-toolkit/
Step 3 — Format the date field
Convert the date to RFC 3339 format with a timezone offset. Use Pacific Time as default if not specified:
YYYY-MM-DDTHH:MM:SS-08:00 # Pacific Standard Time
YYYY-MM-DDTHH:MM:SS-07:00 # Pacific Daylight Time (summer)
Default time: 09:00:00 (9 AM).
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.
- yesterday First seen · 155 lines · 40 tokens per session scan C a103a7ab22da
write-blog is a skill published in the GitHub repository MemMachine/memmachine.github.io (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,444 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…