AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Strato

skill-vivary-dev-vivary-strato-skill · by vivary-dev

>-

No reviews yet
0 installs
27 views
0.0% view→install

Install

$ agentstack add skill-vivary-dev-vivary-strato-skill

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-vivary-dev-vivary-strato-skill)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Strato? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

strato — the agent OS skill

strato's model is the per-turn loop (STRATO.md). This skill is the executable for the loop's slower clock — the per-heartbeat work that makes a workspace compound: set the workspace up, audit it on a cadence, and turn what was learned into durable improvement. Read [../../../STRATO.md](../../../STRATO.md) for the model.

It never re-embeds file contents: the workspace's starter files live in strato's [templates/](../../../templates/) directory and are the single source of truth. Module index.md files are routers, not second copies of the module detail.

Three modes — pick by the workspace state and the request.

bootstrap — first time in a workspace

Use when SOUL.md / USER.md / AGENTS.md / MEMORY.md / STATE.md are missing at the workspace root, or the user says "set up the workspace".

Procedure: explore → interview → confirm → write, laying down the templates/ populated with the user's answers. The interview uses the loop's opener (I think I know / I am inferring / I do not know / please confirm) at the chosen depth (3 / 5 / 8 / 10 questions). Full steps in [references/bootstrap.md](references/bootstrap.md).

heartbeat — periodic audit

Use on a schedule or when the user says "run a heartbeat" / "audit the workspace". Two flavors: light (read-only findings report) and deep (interactive cleanup, per-item prompts). Surfaces stale folders, cross-project bleed, skill candidates, dead skills, automation drift, and playbook gaps. Checklist + report format in [references/heartbeat.md](references/heartbeat.md).

self-improve — capture, extract, package

Use after a slice, a bug, or a confusing handoff, or when the user says "this happened again" / "package this into a skill". Three procedures — the bug-risk playbook, the third-strike skill rule, and workflow-plugin packaging — in [references/self-improvement.md](references/self-improvement.md).

🚦 Gates (mirror STRATO.md — never batch)

  • Never delete or move a file without showing paths and getting per-item

confirmation (require the user to type the name for a delete).

  • Never modify SOUL.md / USER.md / AGENTS.md after bootstrap, or change an

existing skill, without approval.

  • Never publish, push, or send externally without explicit per-item approval.
  • Creating a new SOP/skill/plugin: show the draft first.

Done means

  • The workspace has a discoverable shared brain (the templates/ files, populated)

that survives a session restart.

  • The latest heartbeat report is within the configured cadence.
  • Lessons from the last session landed in bug-risk-playbook.md or a skill — not just

in chat.

  • Any third-strike workflow this session became a skill, a plugin, or an explicit "no".

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.