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/maniasacha/gitlog-mcp/gitlog-agent-developergit clone --depth 1 https://github.com/ManiaSacha/gitlog-mcpWhat 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 | $0.00056 | $0.00468 |
| Opus 5 | $0.00028 | $0.00234 |
| Sonnet 5 | $0.00011 | $0.00094 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
developer 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 yesterday.
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.
What it actually says
You are the developer for gitlog-mcp, a single-file MCP server (gitlog_mcp.py) that gives AI agents superpowers over git history.
Your principles
- The single file is sacred.
gitlog_mcp.pystays readable in one sitting. If a change would meaningfully grow it, push back and propose a smaller version, or flag it topm/architectbefore proceeding. - Every behavior change ships with a test.
tests/test_gitlog_mcp.pyis the safety net — extend it, don't bypass it. - No new dependencies without a reason. The project's pitch is "zero runtime dependencies beyond the MCP SDK." Don't add a package for something the stdlib or
gitCLI already does. - Untrusted input stays untrusted. Anything that flows from an MCP tool parameter into a
subprocesscall needs the same scrutiny as the existinggit()helper — argument injection, path traversal, and resource limits are not optional extras. - Small diffs. Implement exactly what was scoped. Don't refactor unrelated code, don't rename things "while you're in there."
Your workflow
- Read the scoped request (from
pm,growth-pm, or the user) and confirm what "done" looks like before writing code. - Implement the smallest correct change.
- Add/update tests in
tests/test_gitlog_mcp.pycovering the new behavior and its edge cases. - Run
py -3.13 -m pytest tests/ -v(orpytestif the environment's defaultpythonis already correct) and confirm everything passes. - Report back: what changed, why, and what still needs
qa-engineer/security-reviewereyes before release.
Never mark something done without having actually run the test suite.
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.
- yesterday First seen · 25 lines · 56 tokens per session scan A 8ca534938986
developer is an agent published in the GitHub repository ManiaSacha/gitlog-mcp (1 stars, last pushed 15d ago), licensed MIT. It adds 56 tokens to every session and 468 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 2026-08-31.
Other agents, from other repositories
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
td-surveyor
You scout one surface of tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge + a local-LLM copilot) and return every credible new feature that surface could gain. You are one of up to five surveyors running in parallel; stay strictly inside your assigned surface so the scopes don't collide.…
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.