Install
$ agentstack add skill-minwoo19930301-relay10-relay10-orchestrate ✓ 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
DisciplinedRun Orchestrate
Coordinate the other DisciplinedRun skills without turning every request into a large process.
Preflight
- Restate the requested outcome, constraints, and forbidden actions.
- Inspect the repository and current git state before proposing edits.
- If the CLI is available, run
disciplinedrun doctorand preview routing withdisciplinedrun route "" --json(r10remains a legacy alias). - Treat
disciplinedrun run "" --dry-runas a preview. Run a mutating pipeline only when the user authorized implementation.
This skill helps choose a workflow. It does not change the model of the host agent's current task, whether that host is Codex or Claude Code, and does not make unsupported providers available.
Choose the smallest path
- Read-only evidence gathering: use
relay10-researchonly. - Ambiguous or high-impact change: use
relay10-spec, thenrelay10-build. - Approved, well-specified edit: use
relay10-builddirectly. - Failure or regression: use
relay10-debug; edit only when a fix is authorized. - Review request: use
relay10-reviewwithout editing. - Publication or handoff: use
relay10-releaseafter implementation checks pass. - Skill creation or trigger tuning: use
relay10-skill-lab.
Skip stages whose output cannot change the decision. Add review depth as risk, blast radius, irreversibility, or verification difficulty rises.
Handoff contract
For every active stage, record:
- goal and non-goals;
- inputs and evidence locations;
- allowed mutations;
- result and unresolved risks;
- deterministic checks and semantic review;
- next owner or next action.
Separate observed facts, inferences, and proposals. Never call a stage complete from intention alone.
Safety boundaries
- Preserve unrelated work in a dirty worktree.
- Do not broaden authorization from diagnosis to repair, or from local changes to publication.
- Do not hide destructive actions behind a recipe, subagent, hook, or retry loop.
- Stop repeated repair attempts after three materially similar failures and reassess the hypothesis.
- Keep databases, daemons, worktrees, swarms, and GUIs optional rather than core requirements.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: minwoo19930301
- Source: minwoo19930301/relay10
- 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.