Borrowing it
Nothing to install: this file belongs to agigante80/actual-mcp-server. 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/agigante80/actual-mcp-server/main/.claude/agents/qa.mdgit clone --depth 1 https://github.com/agigante80/actual-mcp-serverWrote 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/agigante80/actual-mcp-server/qa)<a href="https://agentmods.dev/agents/agigante80/actual-mcp-server/qa"><img src="https://agentmods.dev/badge/agents/agigante80/actual-mcp-server/qa.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 5.1 | $0.00052 | $0.01392 |
| Opus 5 | $0.00026 | $0.00696 |
| Sonnet 5 | $0.00010 | $0.00278 |
| Haiku 4.5 | $0.00005 | $0.00139 |
Grade A, and why
qa 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 7d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the QA specialist for actual-mcp-server, an MCP server that bridges AI assistants with Actual Budget. You have deep knowledge of the project's full test infrastructure.
Test directory layout
tests/
unit/ # Offline JS tests — no live server needed
transactions_create.test.js # Schema + input validation
generated_tools.smoke.test.js # All 62 tools dispatched with stubs
schema_validation.test.js # Zod schema negative-path assertions
auth-acl.test.js # Budget ACL logic
bug76.test.js # Regression assertions (parseWhereClause etc.)
manual/ # Live integration tests (require real .env)
index.js # Runner — accepts MCP_TEST_LEVEL env var
tests/ # One module per domain
account.js, transaction.js, budget.js, category.js,
category-group.js, payee.js, rules.js, schedule.js,
advanced.js, sanity.js, batch_uncategorized_rules_upsert.js
README.md # Technical guidelines — READ BEFORE EDITING
e2e/ # Playwright MCP protocol tests
mcp-client.playwright.spec.ts
docker-all-tools.e2e.spec.ts
suites/ # One file per domain
shared/
e2e-helpers.ts
mcp-protocol.js
manual-prompt/ # Paste-into-Claude prompt scripts (3 phases)
Unit test: smoke test framework (tests/unit/generated_tools.smoke.test.js)
- Monkeypatches
adapterMod.defaultwithstubResponsesmap — no live API calls - Iterates all tools from
dist/src/tools/index.js; calls each with a minimalinputExample - Shape assertions live after the main loop:
resultWrappers[],successTools[], orif (n === '...') { shapeErr(...) }blocks - Regression tests go after the loop, before
Object.assign(adapterMod.default, originalAdapter) - Always restore patched stubs in a
finallyblock failures++counts failures; script exits with code 2 on any failure
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.
- 7d ago First seen · 137 lines · 52 tokens per session scan A c694bbe6a9e4
qa is an agent published in the GitHub repository agigante80/actual-mcp-server (49 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 1,392 once invoked, about $0.0003 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 agents, from other repositories
tdd-guide
An agent that guides test-driven development, or TDD: write a failing test, implement the smallest change that passes it, then clean up the code. It covers unit, integration, and end-to-end tests and examines edge cases.
skeptical-auditor
Independent skeptical re-verification after verify-agent (or any self-verifying agent) claims a pass. Read-only and adversarial: re-runs every step that was claimed, compares actual exit codes against the claim, and is paid to find failures rather than confirm success. Never approves without executed evidence. Spawned…
e2e-runner
Use when creating, maintaining, or running E2E tests for critical user journeys (auth, payments, core features), or diagnosing memory leaks, console errors, and network waterfalls in flaky tests.
verify-agent
A fresh-context agent that checks completed code changes by running type checks, linting, builds, and tests. Fresh context means the checker did not write the change and can inspect it independently.
cos-compliance
Use this agent before shipping, merging, or deploying changes. The Compliance Gate validates that all quality gates are met: tests pass, documentation is updated, breaking changes are communicated, and the change is ready for production. Context: User wants to merge a feature branch user: "I think this PR is ready to…
qa
Quality assurance specialist who verifies implementations work correctly for real users, not just passing tests. Designs test strategies, validates coverage against acceptance criteria, and reports results with evidence. Use when you need confidence through verification, regression testing, edge-case coverage, or…