AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Orch Infra

skill-zig999-siegard-code-orch-infra · by zig999

Shared infrastructure checks run at the start of every orchestrator cycle — run_preflight.py, run_integrity.py, run_circuit_check.py. Any non-zero exit blocks the cycle with status blocked. Loaded by all orchestrators. Not user-invocable — orchestrators run the scripts directly.

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

Install

$ agentstack add skill-zig999-siegard-code-orch-infra

✓ 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 Used
  • 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-zig999-siegard-code-orch-infra)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo 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 Orch Infra? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

orch-infra

Shared infrastructure skill: run preflight, integrity, and circuit-breaker checks at the start of every orchestrator cycle.

Usage contract

Every orchestrator loads this skill and calls all three scripts at the start of each cycle:

python3 .claude/skills/orch-infra/scripts/run_preflight.py
python3 .claude/skills/orch-infra/scripts/run_integrity.py
python3 .claude/skills/orch-infra/scripts/run_circuit_check.py

On any non-zero exit: stop and return {"status": "blocked"} to the meta-orchestrator.

Output envelope (all scripts)

Every script emits exactly one JSON object to stdout:

| Field | Type | Description | |-------|------|-------------| | status | "ok" \| "blocked" | Pass/fail verdict | | check | string | "preflight" \| "integrity" \| "circuit" | | timestamp | string | ISO 8601 UTC timestamp | | reason | string | Present only on "blocked" — machine-readable failure code | | detail | object | Present only on "blocked" — additional context |

scripts/run_preflight.py

Runs preflight.py --quick (local runtime checks only). Returns blocked if any check fails.

python3 .claude/skills/orch-infra/scripts/run_preflight.py

Exit codes: 0 = all checks passed, 1 = at least one check failed or exec error.

Example output (ok):

{"status": "ok", "check": "preflight", "timestamp": "...", "passed": 5, "total": 5, "failed_count": 0}

Example output (blocked):

{
  "status": "blocked",
  "check": "preflight",
  "timestamp": "...",
  "reason": "preflight_failed",
  "passed": 4,
  "total": 5,
  "failed_count": 1,
  "failed_checks": [{"check": "flock_works", "reason": "fcntl not available"}]
}

scripts/run_integrity.py

Verifies the hash chain of the orchestration log in strict mode. Returns ok if no log exists (first run).

python3 .claude/skills/orch-infra/scripts/run_integrity.py

Exit codes: 0 = chain intact (or no log), 1 = chain invalid or error.

Example output (ok):

{"status": "ok", "check": "integrity", "timestamp": "...", "events_verified": 42}

Example output (blocked):

{
  "status": "blocked",
  "check": "integrity",
  "timestamp": "...",
  "reason": "chain_invalid",
  "events_verified": 41,
  "first_error_seq": 42,
  "truncation_candidate": 42
}

scripts/runcircuitcheck.py

Evaluates circuit breaker state. Returns blocked if the circuit is tripped or should trip. Returns ok if no log exists (first run).

python3 .claude/skills/orch-infra/scripts/run_circuit_check.py

Exit codes: 0 = circuit open (healthy), 1 = circuit tripped or evaluation error.

Example output (ok):

{"status": "ok", "check": "circuit", "timestamp": "...", "tripped": false, "failure_count": 2, "threshold": 50}

Example output (blocked):

{
  "status": "blocked",
  "check": "circuit",
  "timestamp": "...",
  "reason": "circuit_tripped",
  "tripped": true,
  "failure_count": 52,
  "threshold": 50
}

What orch-infra does NOT do

  • Does not know about phases or domains
  • Does not read spec files or delivery artifacts
  • Does not interact with humans
  • Does not emit events to the log

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.