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 agentmods add commands/holgerleichsenring/agent-smith/smokegit clone --depth 1 https://github.com/holgerleichsenring/agent-smithWrote 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/commands/holgerleichsenring/agent-smith/smoke)<a href="https://agentmods.dev/commands/holgerleichsenring/agent-smith/smoke"><img src="https://agentmods.dev/badge/commands/holgerleichsenring/agent-smith/smoke.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.01260 |
| Opus 5 | $0.00017 | $0.00630 |
| Sonnet 5 | $0.00007 | $0.00252 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
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 5d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running the agent-smith smoke suite. The goal is a fast, deterministic answer to "does the binary actually work?" — every phase merge should end with a green smoke before being declared done.
How to run
The first argument selects scope. Default is fast (no LLM cost).
/smokeor/smoke fast— build + tests + CLI binary boots + docker-compose config validates. ~2 minutes, no LLM./smoke api-scan—fastplus a real api-scan against the configured local target./smoke security-scan—fastplus a real security-scan against the agent-smith repo./smoke fix-bug—fastplus a dry-run of fix-bug against a known ticket./smoke demo—fastplusagentsmith demoend-to-end on the bundled sample project (p0326). Costs real LLM tokens (one small fix-bug run); needs only a config with one agent + its key. PASS = exit 0 and the printedgit diff HEAD~1shows the PriceCalculator boundary fix./smoke all— fast + all three deep scans sequentially.
Steps for fast (always run)
Run these in order. Any non-zero exit ends the smoke as FAIL.
- Build:
dotnet build— 0 errors, 0 warnings. Warnings count as failures unless they're the knownSandboxToolHostobsoletes (5 max). - Tests:
dotnet test --no-build. All passing. - CLI binary boot:
dotnet run --no-build --project src/AgentSmith.Cli -- --help— exits 0, prints the command list. - CLI pipeline dry-runs: for each of
api-scan,security-scan,fix,feature,demo:dotnet run --no-build --project src/AgentSmith.Cli -- <command> --help— exits 0. - docker-compose config validates:
docker compose -f deploy/docker-compose.yml config -q— exits 0. (Skip silently ifdeploy/docker-compose.ymldoesn't exist on this branch.)
Report per step: PASS / FAIL with a one-line summary.
Steps for api-scan (in addition to fast)
The operator has a local SampleA instance at https://localhost:49190 (target may differ; check .env / shell env first). Use the project name sample-a-api-security-azure-openai. Required env: AZURE_OPENAI_API_KEY, AZURE_DEVOPS_TOKEN.
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.
- 5d ago First seen · 96 lines · 35 tokens per session scan A 758a7dd80fde
smoke is a command published in the GitHub repository holgerleichsenring/agent-smith (23 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 1,260 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 2026-08-30.
Other commands, from other repositories
tests
Test coverage quality analysis — behavioral coverage, critical gap identification, test resilience evaluation.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
create-issue
Transform feature descriptions, bug reports, or improvement ideas into well-structured GitHub issues.
compose-test
Run Compose UI tests with Espresso. Verify critical user flows.
kaku-runtime-test
测试 Agent 用 Kaku 管理编程团队的完整端到端流程。 起点永远是 inject（模拟飞书消息），不直接调用内部 CLI。.