Borrowing it
Nothing to install: this file belongs to OctopusGarage/alcove. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/OctopusGarage/alcove/main/.agents/skills/alcove-smoke/SKILL.mdgit clone --depth 1 https://github.com/OctopusGarage/alcoveWrote 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/octopusgarage/alcove/alcove-smoke)<a href="https://agentmods.dev/skills/octopusgarage/alcove/alcove-smoke"><img src="https://agentmods.dev/badge/skills/octopusgarage/alcove/alcove-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/octopusgarage/alcove/alcove-smoke"><img src="https://agentmods.dev/badge/skills/octopusgarage/alcove/alcove-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 | $0.00038 | $0.01095 |
| Opus 5 | $0.00019 | $0.00548 |
| Sonnet 5 | $0.00008 | $0.00219 |
| Haiku 4.5 | $0.00004 | $0.00110 |
Grade A, and why
alcove-smoke scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alcove Smoke
Run Alcove verification suites from the repository root. If the current working directory is unclear, locate it first:
repo="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
cd "$repo"
Commands
Top-level scripts/*.sh files are stable wrappers. Implementations live under
scripts/verify/.
Fast isolated smoke:
scripts/smoke.sh
Keep isolated artifacts for debugging:
ALCOVE_SMOKE_KEEP=1 scripts/smoke.sh
Read-mostly real home smoke:
ALCOVE_REAL_SMOKE_REPORT_DIR=.tmp/real-home-smoke scripts/smoke-real-home.sh
High-cost real integrations:
scripts/smoke-real-integrations.sh
Agent-client entry smoke:
scripts/smoke-agent-clients.sh
Focused deep smokes:
scripts/smoke-mcp-matrix.sh
scripts/smoke-dashboard-browser.sh
scripts/smoke-radar-reports.sh
scripts/smoke-export-restore.sh
scripts/smoke-messy-inbox.sh
If Clipsmith is not cloned as ../clipsmith, set:
ALCOVE_CLIPSMITH_ROOT=/path/to/clipsmith scripts/smoke-real-integrations.sh
Full project gate:
scripts/check.sh
Repository-selected agent gate:
scripts/agent-quality-gate.sh --mode coach
AI quality eval:
scripts/eval-ai.sh
Focused AI eval for a known risk area:
ALCOVE_AI_EVAL_SUITES=isolated,mcp_matrix ALCOVE_AI_EVAL_PROVIDER=none ALCOVE_AI_EVAL_RUN_CHECK=0 scripts/eval-ai.sh
ALCOVE_AI_EVAL_SUITES=isolated,mcp_matrix ALCOVE_AI_EVAL_SKIP_REFRESH=1 scripts/eval-ai.sh
Focused data/OKF health check for the current machine:
alcove health --home "${ALCOVE_HOME:-$HOME/.alcove}" --json
Use --kb <name> --fix when a managed KB and safe derived-index rebuilds should
be included.
Generate the packet and prompt without calling an AI provider:
ALCOVE_AI_EVAL_PROVIDER=none scripts/eval-ai.sh
Selection
- Use
scripts/smoke.shby default after Alcove application or CLI changes. - Use
scripts/smoke-real-home.shwhen global home, dashboard, pins, tasks, prompts, projects, mounts, connectors, or search changed. - Use
scripts/smoke-real-integrations.shonly when explicitly requested or when capture, Apple Notes, GitHub Stars, OCR, connector external IO, or MCP stdio changed. It reads local Notes.app data and performs network requests. - Use
scripts/smoke-agent-clients.shwhen Hub/KB entry installation, Codex skills, Claude commands, or MCP client routing changed. - Use
scripts/smoke-mcp-matrix.shwhen MCP tool routing or payloads changed. - Use
alcove health --home ... --kb ... --fix --jsonwhen OKF files, indexes, mounts, connectors, pins, prompts, or catalog generation changed. - Use
scripts/smoke-dashboard-browser.shwhen dashboard frontend, snapshot, route, or search behavior changed. - Use
scripts/smoke-radar-reports.shwhen radar presets, scoring, report content, or report HTML/CSS changed. - Use
scripts/smoke-export-restore.shwhen export, backup, home/KB registry, or migration behavior changed. - Use
scripts/smoke-messy-inbox.shwhen inbox reading, capture bundles, truncation, warnings, OCR, or review surfaces changed. - Use
scripts/eval-ai.shwhen the user asks for AI eval or when quality of summarization, classification, dashboard usefulness, agent prompts, or workflow intent routing matters. - Prefer
scripts/agent-quality-gate.sh --mode coach --jsonto choose focusedALCOVE_AI_EVAL_SUITES; do not run full AI eval by habit during normal regression work. - Use
scripts/agent-quality-gate.sh --mode coachwhen the user asks whether the current change needs smoke/eval, or when the changed files span multiple modules and the correct verification set is not obvious. - Use
scripts/check.shbefore claiming code changes are complete.
What ships with it
1 file 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.
- 11d ago First seen · 146 lines · 38 tokens per session scan A 77f19fbf8008
alcove-smoke is a skill published in the GitHub repository OctopusGarage/alcove (0 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 1,095 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
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
api-testing
Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.
add-test
Scaffold a test file for an existing tool, resource, or service. Use when the user asks to add tests, improve coverage, or when a definition exists without a matching test file.
starcat-ui-prototype
A design skill for creating macOS interface prototypes and visual designs for Starcat, a GitHub star-management and AI knowledge-organising app. It follows Apple’s Liquid Glass design language for macOS 26.
write-tests
Generate unit tests for existing code.
moore-wechat-article-downloader
A tool for downloading public WeChat Official Account articles and collecting article histories. WeChat Official Accounts are Chinese publisher or business pages, and the tool supports login, account selection, and scheduled syncing when required.