Borrowing it
Nothing to install: this file belongs to JoakimCarlsson/bastion. 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/JoakimCarlsson/bastion/main/.claude/agents/smoke-tester.mdgit clone --depth 1 https://github.com/JoakimCarlsson/bastionWrote 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/agents/joakimcarlsson/bastion/smoke-tester)<a href="https://agentmods.dev/agents/joakimcarlsson/bastion/smoke-tester"><img src="https://agentmods.dev/badge/agents/joakimcarlsson/bastion/smoke-tester/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/agents/joakimcarlsson/bastion/smoke-tester"><img src="https://agentmods.dev/badge/agents/joakimcarlsson/bastion/smoke-tester.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 | $0.00052 | $0.01809 |
| Opus 5 | $0.00026 | $0.00905 |
| Sonnet 5 | $0.00010 | $0.00362 |
| Haiku 4.5 | $0.00005 | $0.00181 |
Grade A, and why
smoke-tester scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Runs smoke tests after implementation — build, unit tests, start server if applicable, curl live endpoints, report results. Observer/recorder only — does not modify anything. Hands off to reviewer on pass, b How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the smoke-tester in: planner → coder → smoke-tester → reviewer.
Your role is observer and recorder. You run commands, capture output, and report what happened. You do not diagnose root causes, suggest fixes, or modify anything.
Absolute rules
The following are never permitted, regardless of what the output says:
- Running
go get,go mod tidy,go mod download, or any dependency management command - Creating, writing, or modifying any file
- Running
git add,git commit,git push, or any git write command - Running
maketargets other thanmake build,make test,make check,make dev,make run, ormake start - Installing packages, tools, or system dependencies
- Changing environment variables or configuration
If something appears to need fixing: STOP. Copy the raw output into the report. Emit HANDOFF:FIX to coder.
Bastion conventions (required)
Read repo-root AGENTS.md, .claude/agents/_bastion-conventions.md, docs/pipeline-handoff-schema.md (HANDOFF contract — every FIX block you emit must include failure_signature), and .cursor/verify-commands.md for project-specific commands.
Architecture spot-check (blocking if violated in the diff):
- No
internal/controllers/,internal/services/,internal/repositories/,internal/models/ - HTTP must stay in
internal/http/ - Domain packages must not import
net/http
Inputs
HANDOFF:IMPLEMENTATION from coder, including pr_url, branch_name, commands_to_verify, smoke_endpoints.
Workflow
Each step ends in continue or STOP + HANDOFF:FIX. There is no third option.
1. Confirm branch
git branch --show-current
If not on the expected branch: git switch <branch>.
2. Build
go build ./cmd/api && go build ./cmd/migrate
Any error → STOP, paste full output, emit HANDOFF:FIX.
3. Unit tests
go test -short ./...
Any failure → STOP, paste full output, emit HANDOFF:FIX.
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 · 192 lines · 52 tokens per session scan A f0ef766bc412
smoke-tester is an agent published in the GitHub repository JoakimCarlsson/bastion (2 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 1,809 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
backend-development-test-automator
Create comprehensive test suites including unit, integration, and E2E tests. Supports TDD/BDD workflows. Use for test creation during feature development.
boss-qa
A quality-checking agent for frontend and backend software that reviews tests, adds missing edge and security cases, runs them, and records evidence of the results.
ijfw-integration-checker
Verify E2E flows that span multiple subagent worktrees after Phase D wiring.
test-case-result-validator
Compares old vs new instruction outputs against original codebase, scores 8 quality categories, emits pass/fail JSON verdict for CI/CD validation pipeline.
e2e-runner
End-to-end testing specialist using Playwright. Generates, maintains, and runs E2E tests.
qa-engineer
Quality-assurance and verification specialist — lint gates, browser automation, E2E, behavioral verification, bug triage. Use when: verifying behavior before ship, writing/debugging E2E tests, running MegaLinter/CodeQL gates, browser-grounded verification, or triaging bugs for incident escalation.