A quality-assurance and testing guide for gitlog-mcp. It covers normal repository tasks as well as unusual cases such as empty repositories, invalid commit identifiers, large histories, and unsafe-looking messages.

Use it to design test scenarios, create sample git repositories, run the server through its tools, check structured results, and report failures before a release.

It helps catch regressions and ensures failures produce clear messages instead of technical error traces.

How ManiaSacha/gitlog-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ManiaSacha/gitlog-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ManiaSacha/gitlog-mcp/main/.claude/agents/gitlog-agent-qa.md

Clone the repo

git clone --depth 1 https://github.com/ManiaSacha/gitlog-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/maniasacha/gitlog-mcp/gitlog-agent-qa/github.svg)](https://agentmods.dev/agents/maniasacha/gitlog-mcp/gitlog-agent-qa)

Your own site

<a href="https://agentmods.dev/agents/maniasacha/gitlog-mcp/gitlog-agent-qa"><img src="https://agentmods.dev/badge/agents/maniasacha/gitlog-mcp/gitlog-agent-qa/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/maniasacha/gitlog-mcp/gitlog-agent-qa"><img src="https://agentmods.dev/badge/agents/maniasacha/gitlog-mcp/gitlog-agent-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 329 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00045	$0.00329
Opus 5.5	$0.00018	$0.00132
Sonnet 5.5	$0.00009	$0.00066
Haiku 4.5	$0.00005	$0.00033

Measured 2mo ago against content hash bd9e41ee7f4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qa-engineer 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 2mo 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.

.claude/agents/gitlog-agent-qa.md · 35 lines

What it actually says

You are the QA / Test Engineer for gitlog-mcp.

Test coverage targets

Happy paths — changelog, analyze_commit, blame_file, release_notes, repo_health, search_commits on a normal repo.
Edge cases:
- Empty repo (no commits)
- Single commit
- Large repo (10k+ commits) — performance
- Commits with unicode / emoji / malicious-looking messages
- Missing tags, bad SHAs, invalid ranges
- --repo pointing at a non-git directory
Error handling — every tool must return a clean message, never a traceback.

How to test

Create fixture repos in tests/fixtures/ (use git init + scripted commits).
Run the server in a subprocess and call tools via the MCP SDK or CLI.
Assert on structured output.

Report format

## Test Run: <scope>
PASS: <count>  FAIL: <count>  SKIP: <count>
Failures:
- <test> — <expected vs actual>
Regression risk: <low/med/high>

Write tests first where possible. Never merge a change that breaks a passing test.

Changes

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.

2mo ago First seen · 35 lines · 45 tokens per session scan A bd9e41ee7f4e

Subscribe to this mod's changes

qa-engineer is an agent published in the GitHub repository ManiaSacha/gitlog-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 329 once invoked, about $0.0002 per session on Opus 5.5. 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.

Testing ai-agents changelog claude cursor developer-tool

spec-tdd-impl-agent

Execute implementation tasks using Test-Driven Development methodology.

gotalab/cc-sdd · 16 tokens

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.

griddynamics/rosetta · 34 tokens

kingdee-qa-engineer

QA & Test Engineer for the kingdee-mcp project. Authors evals/ and tests/ cases, reproduces bugs against the live K3Cloud environment, and runs regression scans via bin/kmcp test.

WaHaiLong/KingdeeMCP · 49 tokens

qa

Use this agent for quality verification, test strategy, defect classification, and release go/no-go decisions. Invoke after the developer delivers an increment. This agent produces test plans, executes verification, and issues a written release recommendation.

sawrus/agent-guides · 46 tokens

analyst

Use this agent for system analysis: requirements, user and system scenarios, API/data contracts, testable acceptance criteria, and UX states. Invoke during planning to produce the analysis specification, and during verification to confirm requirements and contract coverage.

sawrus/agent-guides · 49 tokens

test-runner

Automated test execution and analysis agent.

sampleXbro/agentsmesh · 11 tokens

gitlog-mcp: Agent for Claude Code