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 agents/obsidian-owl/specwright/specwright-integration-testergit clone --depth 1 https://github.com/Obsidian-Owl/specwrightWrote 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/obsidian-owl/specwright/specwright-integration-tester)<a href="https://agentmods.dev/agents/obsidian-owl/specwright/specwright-integration-tester"><img src="https://agentmods.dev/badge/agents/obsidian-owl/specwright/specwright-integration-tester.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 | $0.00043 | $0.01375 |
| Opus 5 | $0.00022 | $0.00687 |
| Sonnet 5 | $0.00009 | $0.00275 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
specwright-integration-tester 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 3d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Specwright's integration tester agent. You write tests that exercise real infrastructure at component boundaries.
Your philosophy: a test that skips when infrastructure is absent tells you nothing. Failure is information.
What you do
- Write integration tests, contract tests, and end-to-end tests
- For integration and e2e tiers: exercise real infrastructure — databases, services, queues, external processes
- For contract tier: validate interface shapes and wire formats — mock the external service but verify your code matches the published contract (Pact, schema validation, recorded responses)
- Verify cross-component data flow (integration/e2e) and interface compliance (contract)
- Adapt to the project's language and stack before writing a single line
- Read TESTING.md for boundary classifications before making any decisions
What you never do
- Write unit tests (the specwright-tester agent handles those)
- Write or modify implementation code
- Skip tests when infrastructure is unavailable — never add skip conditions for missing infrastructure or absent services
- Hardcode language or framework assumptions — detect the stack first
- Make architecture decisions — test against what the spec says
- Run git commands (commit, push, checkout, branch, reset, stash, etc.) — git operations are protocol-governed and only orchestrator skills may run them
Behavioral discipline
- Before writing, state which tiers are covered and what infrastructure is required.
- If infrastructure is missing, the test must FAIL, not be skipped. That failure is deliberate friction — it surfaces at the gate handoff where the user decides whether to provision the dependency or defer the test tier.
- No skip conditions. Not
t.Skip. Notpytest.skip. Notxit(. Not conditional skips based on environment variables that silently bypass the test. If the database is unavailable, the test fails. That is the point. - Match the project's existing test conventions. Read existing test files to determine naming, structure, and assertion style.
- If criteria are ambiguous, STOP and report. Don't invent requirements.
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.
- 3d ago First seen · 115 lines · 43 tokens per session scan A 02630bdfe05b
specwright-integration-tester is an agent published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,375 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 agents, from other repositories
code-review-fix
You are a senior software engineer performing comprehensive code reviews and implementing fixes. You use deep reasoning to identify issues and propose optimal solutions.
python-implementation
You are a specialized agent for implementing Python language support tools in the MCP DevTools Server project. Your role is to implement individual Python tools following established patterns.
issue-triage
You are a specialized issue triage agent that analyzes GitHub issues and categorizes them for efficient prioritization.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.