Install
$ agentstack add skill-wyattowalsh-agents-cross-agent-install-smoke ✓ 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
Cross-Agent Install Smoke
Validate additive skills sync without mutating live harness installs.
Scope: Install smoke only. Do not run live apply installs unless the maintainer explicitly requests it.
Dispatch
| $ARGUMENTS | Action | |------------|--------| | Empty / phase1 / dry-run | Run phase 1 dry-run JSON assertions | | phase2 / local / smoke | Run phase 2 temp-HOME smoke (requires INSTALL_SMOKE=1) | | all | Run phase 1, then phase 2 when gated | | help | Show phases, gates, and example commands |
Phase 1 — Dry-Run JSON
Run the deterministic checker from the repo root:
uv run python skills/cross-agent-install-smoke/scripts/dry_run.py
Phase 1 executes the repo skills-sync dry-run command and asserts:
- top-level keys:
ok,mode,inventory_count,include_installed,agents modeisdry-run- each agent row includes
agentplus list fieldsmissing,already_present,unresolved,skipped
Pass criteria: script exits 0 and prints a JSON summary to stdout.
Phase 2 — Temp-HOME Smoke
Phase 2 is opt-in and mutates only a temporary home directory.
INSTALL_SMOKE=1 uv run python skills/cross-agent-install-smoke/scripts/local_smoke.py
The script:
- Refuses to run unless
INSTALL_SMOKE=1 - Creates an isolated
HOMEunder a temp directory - Runs the repo validation command against the repo
- Runs a single-harness skills-sync dry-run JSON probe
- Cleans up the temp home
Never point phase 2 at a production home directory.
Validation Contract
uv run python skills/cross-agent-install-smoke/scripts/check.py
INSTALL_SMOKE=1 uv run python skills/cross-agent-install-smoke/scripts/check.py
Completion criteria:
- Phase 1 (
dry_run.py) exits0in CI and local maintainer runs. - Phase 2 runs only when
INSTALL_SMOKE=1is set. scripts/check.pyexits0for the selected phase gates.
Critical Rules
- Default to dry-run; never apply live installs from this skill.
- Treat skills sync JSON as evidence, not authority over repo policy.
- Run phase 1 before recommending any cross-harness install reconciliation.
- Gate phase 2 behind
INSTALL_SMOKE=1and a disposable tempHOME. - Report harness-specific inventory errors without masking top-level
ok: false.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: wyattowalsh
- Source: wyattowalsh/agents
- License: MIT
- Homepage: https://agents.w4w.dev
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.