Install
$ agentstack add skill-danmcinerney-orchflows-orch-visualize ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Require: the subject — supplied or named content only; gather no new evidence and decide nothing about the subject. Label every inferred connection inferred.
Choose the diagram by the subject's own shape — for a skill or workflow, resolve every backticked call recursively; stop on a missing dependency or cycle and say so. Preserve what the subject states: order, branches, parallel lanes, loop bounds and exits, failure returns. Conditional or weak edges dotted; defect edges red; cycles as real back-edges.
Write Mermaid blocks plus at most one terse paragraph per diagram — what it shows and the one thing to notice — to .orch/runs/viz/.md unless the caller names a path. Verify before returning: run this package's scripts/verify_mermaid.py on the output; one correction pass on rejection, then stop. Report verified only after exit 0, with graph count; otherwise return failed with the verifier's diagnostic. On the dispatch's request, render the verified page with scripts/render_html.py — a self-contained .html beside the source — and report its mode (cdn mode is degraded).
Never: decorate beyond the subject's own vocabulary; describe an unverified page as verified; add evidence the subject did not supply.
Return: status, file path, graph count, verifier evidence, and the per-diagram explanations; rendered page path with mode only on request.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: DanMcInerney
- Source: DanMcInerney/orchflows
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.