Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add wyattowalsh/agents --skill cross-agent-install-smokegit clone --depth 1 https://github.com/wyattowalsh/agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wyattowalsh/agents/cross-agent-install-smoke)<a href="https://agentmods.dev/skills/wyattowalsh/agents/cross-agent-install-smoke"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/cross-agent-install-smoke/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wyattowalsh/agents/cross-agent-install-smoke"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/cross-agent-install-smoke.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.00749 |
| Opus 5 | $0.00021 | $0.00375 |
| Sonnet 5 | $0.00008 | $0.00150 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
cross-agent-install-smoke scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 bucket fieldsmissing,already_present,unresolved,skipped - bucket fields may be legacy string lists or compact objects
{count, sample, truncated}(Wave 1b+ default JSON) - when present, optional buckets (
projection_ensure,projection_blocked,store_missing,internal_projection,pin_blocked) use the same shapes
Pass criteria: script exits 0 and prints a JSON summary to stdout. Phase 1 is dry-run only — never --apply.
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
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 85 lines · 42 tokens per session scan A c0a7f6e4c212
cross-agent-install-smoke is a skill published in the GitHub repository wyattowalsh/agents (5 stars, last pushed 8d ago), licensed MIT. It adds 42 tokens to every session and 749 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.