mstack

A workflow that guides software tasks through understanding, design, specification, implementation, verification, review, and release. It also keeps progress and evidence on disk.

In plain words
What is it for?
Use it when investigating behavior, fixing bugs, building features, refactoring code, or completing a task end to end.
Why use it?
It gives the work a recorded process with checks and approval boundaries, so important steps are less likely to be skipped.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/romerma/mstack/router
Any agent
npx skills add romerma/mstack --skill router
Clone the repo
git clone --depth 1 https://github.com/romerma/mstack

Made for: Claude Code, Codex.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,708 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00075 $0.01708
Opus 5 $0.00037 $0.00854
Sonnet 5 $0.00015 $0.00342
Haiku 4.5 $0.00007 $0.00171

Measured yesterday against content hash b31ead69f6c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mstack 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 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.

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.

skills/router/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mstack

You are running under mstack. Two things are true here that are not true by default: the work has to leave evidence on disk, and nobody approves their own work.

$ARGUMENTS

First, orient

  1. mstack gate. A red gate stops you. Report it; do not work around it.
  2. mstack state active. If something is in flight, read .mstack/progress/current.md and resume its recorded next step rather than starting over.
  3. Match the request to a playbook below, and copy that playbook's steps into your todo list verbatim, before any task-specific todos and before you reason about the task.

That third step is the one that gets skipped. The failure mode is reading a playbook, then writing a bespoke plan that quietly drops its named steps. A step you choose not to do stays in the list with a one-line skip: <reason>. Skipping silently is not allowed.

Route

The request is about Playbook
Understanding how something works, or why it is the way it is investigate
Something broken, wrong, or slower than it should be bug-fix
Building something new feature
Changing structure without changing behaviour refactor
Proving a change actually works /mstack:verify
Judging work that already exists /mstack:review
Getting a change merged /mstack:ship
Writing the commit message, or a PR title /mstack:commit
A program of work across many changes orchestrate
Picking up an interrupted session resume
Clearing out dead branches and worktrees cleanup

Nothing fits? Say so, then design a playbook for this task in the same shape as the ones above and follow it. Do not fall back to improvising without a written plan.

The two paths

Most work goes straight to implementation. The spec path is opt-in, and it turns on when any of these is true:

Read the full file on GitHub · 146 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. yesterday First seen · 146 lines · 75 tokens per session scan A b31ead69f6c1

Subscribe to this mod's changes

mstack is a skill published in the GitHub repository romerma/mstack (1 stars, last pushed 8d ago), licensed MIT. It adds 75 tokens to every session and 1,708 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

happiness-skill

当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.

kangarooking/cangjie-skill · 136 tokens

gsd-audit-milestone

Audit milestone completion against original intent before archiving.

open-gsd/gsd-core · 17 tokens

spec-kitty-charter-doctrine

Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…

Priivacy-ai/spec-kitty · 135 tokens

spec-kitty-spdd-reasons

Drive REASONS Canvas authoring and review for Spec Kitty missions that opted in to Structured-Prompt-Driven Development (SPDD) via charter selection. Triggers: "use SPDD", "use REASONS", "generate a REASONS canvas", "apply structured prompt driven development", "make this mission SPDD". Does NOT handle: enforcing SPDD…

Priivacy-ai/spec-kitty · 118 tokens

dependency-upgrade

Plan, batch, and verify dependency upgrades safely. Triages outdated packages into risk tiers, upgrades in order (dev/minor/patch first, runtime majors last), verifies each batch, and produces an auditable commit sequence. Use when asked to "upgrade deps", "bump packages", "update nodemodules", "fix vulnerabilities"…

open-gsd/gsd-pi · 90 tokens

forensics

Post-mortem a failed GSD auto-mode run. Traces symptom to root cause via .gsd/ activity, journal, metrics, and lock artifacts, producing a filing-ready bug report with file:line refs and a fix suggestion. Use when asked to "forensics", "post-mortem", "why did auto-mode fail", "trace the stuck loop", "debug the crash"…

open-gsd/gsd-pi · 112 tokens