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/hugo-choresnpx skills add MemMachine/memmachine.github.io --skill hugo-choresgit 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 | $0.00048 | $0.03265 |
| Opus 5 | $0.00024 | $0.01632 |
| Sonnet 5 | $0.00010 | $0.00653 |
| Haiku 4.5 | $0.00005 | $0.00327 |
Grade E, and why
hugo-chores scanned grade E with 4 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s https://go.dev/dl/?mode=json | python3 -c "import sys,json; data=json.load(sys.stdin); stable=[r for r in data if r.get('stable')]; print(stable[0]['version'] if stable else 'not found')" Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -rn "[0-9]\+\.[0-9]\+\.[0-9]\+" README.md AGENTS.md .claude/CLAUDE.md 2>/dev/null | grep -i "hugo\|sass\|go\|node" Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
If no subcommand is given, print the usage above and list the available subcommands with one-line descriptions. Do not run any commands. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://api.github.com/repos/gohugoio/hugo/releases/latest | grep '"tag_name"' How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hugo-chores
Perform maintenance tasks on the MemMachine website repository. Subcommands handle Hugo version upgrades, build verification, npm dependency updates, and vendored theme library updates.
Usage
/hugo-chores # show available subcommands
/hugo-chores upgrade-hugo # update Hugo version in CI/CD and docs
/hugo-chores verify-build # run a production build and report results
/hugo-chores update-npm # audit and update npm dependencies
/hugo-chores update-theme # check and update vendored theme libraries
Deployment Model
The site deploys automatically. Every push to main triggers the GitHub Actions workflow at .github/workflows/hugo.yaml, which builds the site with Hugo and deploys the output to GitHub Pages. There is no manual deploy step — merging a PR to main is the deploy.
All tool versions are pinned as env: vars at the top of that workflow file:
env:
DART_SASS_VERSION: 1.99.0
GO_VERSION: 1.26.3
HUGO_VERSION: 0.161.1
NODE_VERSION: 22.22.3
To upgrade any tool, edit the corresponding env var in .github/workflows/hugo.yaml and push to main.
What You Must Do When Invoked
If no subcommand is given, print the usage above and list the available subcommands with one-line descriptions. Do not run any commands.
If a subcommand is given, follow the steps for that subcommand below.
Subcommand: upgrade-hugo
Upgrades the Hugo version used in CI/CD and updates all version references in documentation.
Step 1 — Find the current version
grep -n "HUGO_VERSION\|DART_SASS_VERSION\|GO_VERSION\|NODE_VERSION" .github/workflows/hugo.yaml | head -10
Parse all four pinned versions from the workflow file.
Step 2 — Find the latest releases
Run these in parallel:
curl -s https://api.github.com/repos/gohugoio/hugo/releases/latest | grep '"tag_name"'
curl -s https://api.github.com/repos/sass/dart-sass/releases/latest | grep '"tag_name"'
curl -s https://go.dev/dl/?mode=json | python3 -c "import sys,json; data=json.load(sys.stdin); stable=[r for r in data if r.get('stable')]; print(stable[0]['version'] if stable else 'not found')"
curl -s https://nodejs.org/dist/index.json | python3 -c "import sys,json; releases=[r for r in json.load(sys.stdin) if r['version'].startswith('v22.') and 'lts' in r and r['lts']]; print(releases[0]['version'] if releases else 'not found')"
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 · 364 lines · 48 tokens per session scan E 87d558fde41d
hugo-chores is a skill published in the GitHub repository MemMachine/memmachine.github.io (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 3,265 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it E with 4 findings (downloads and executes remote code, reads agent configuration directories, unrestricted tool access). 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.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.