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/matthewdigiuseppe/mstack/freezenpx skills add matthewdigiuseppe/MStack --skill freezegit clone --depth 1 https://github.com/matthewdigiuseppe/MStackWrote 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/matthewdigiuseppe/mstack/freeze)<a href="https://agentmods.dev/skills/matthewdigiuseppe/mstack/freeze"><img src="https://agentmods.dev/badge/skills/matthewdigiuseppe/mstack/freeze.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 | $0.00048 | $0.00593 |
| Opus 5 | $0.00024 | $0.00296 |
| Sonnet 5 | $0.00010 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
freeze 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 4d 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.
What it actually says
/mstack:freeze
Stage: power Voice: safety
Argument
$ARGUMENTS — the directory writes are allowed within (relative to the paper folder, e.g. submission or paper/sections). All writes outside it are denied until /mstack:unfreeze.
If no argument is given, do not set a lock. Print the current freeze state from .mstack/safety.yaml and ask which directory to lock to — a lock on the whole paper folder would be a no-op and give false comfort.
How it's enforced
MStack's PreToolUse hook (hooks/mstack-guard.py) reads .mstack/safety.yaml before every Write, Edit, and Bash call. While freeze.path is set, writes outside that directory are denied by the hook itself — including in later sessions that never loaded this skill. .mstack/ stays writable so the lock can be cleared, and data/raw/ stays read-only regardless of the freeze.
Procedure
-
Read or create
.mstack/safety.yaml. -
Set the lock (the hook parses this exact shape):
freeze: path: "submission" set_at: "YYYY-MM-DD HH:MM" -
Behavior while the lock is set:
Write/Editoutsidefreeze.path(and outside.mstack/): denied by the hook.- Mutating
Bashcommands (rm,mv,cp, redirects,sed -i,git reset/clean/checkout --) whose targets resolve outside the lock: denied; when the hook can't resolve the targets, it asks for confirmation instead. - Reads, greps, and non-mutating commands are unaffected.
-
Print the lock state to the user with the absolute path of the lock target.
Outputs
.mstack/safety.yamlupdated.- Summary: lock target.
Anti-patterns to refuse
- Quietly working around the lock. If a step requires a write outside, surface it and ask — don't restructure the work to dodge the hook.
When to call other skills
- Pair with
/mstack:carefulto make/mstack:guard. - Use
/mstack:unfreezeto clear.
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.
- 4d ago First seen · 59 lines · 48 tokens per session scan A 21168083a1a4
freeze is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 8d ago), licensed MIT. It adds 48 tokens to every session and 593 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.
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…