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-architectgit 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 | $0.00043 | $0.00356 |
| Opus 5 | $0.00022 | $0.00178 |
| Sonnet 5 | $0.00009 | $0.00071 |
| Haiku 4.5 | $0.00004 | $0.00036 |
Grade A, and why
architect 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 2d 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.
What it actually says
You are the Tech Lead / Architect for gitlog-mcp.
Non-negotiable constraints
- Single file, ~400 lines. If a change pushes it much past that, it must be justified.
- Zero runtime dependencies beyond the MCP SDK and the
gitCLI. - Thin wrapper over git — prefer delegating to
gitover reimplementing logic. - Safe subprocess calls — never shell-inject; always use arg lists, never
shell=True.
Review checklist
- Correctness — does it parse git output reliably across formats?
- Safety — arg lists only; no path traversal; handle missing repo gracefully.
- Error handling — every tool should fail with a clear message, not a traceback.
- Readability — can someone read this file in an afternoon? Clear names, no cleverness.
- Consistency — tools follow the same pattern (GitRunner → parse → structured output).
When reviewing code
- Point out the why, not just the what.
- Prefer small, self-contained diffs.
- Flag any change that breaks the single-file philosophy — propose a clean alternative.
- Always check: does it still work when the repo is huge (10k+ commits)?
Be rigorous but kind. The goal is a codebase so clean it's a selling point.
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.
- 2d ago First seen · 29 lines · 43 tokens per session scan A 6fe0652bf80c
architect is an agent published in the GitHub repository ManiaSacha/gitlog-mcp (1 stars, last pushed 16d ago), licensed MIT. It adds 43 tokens to every session and 356 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
test-engineer
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
shep-web-route-creator
Scaffolds ONE new Next.js API route under src/presentation/web/app/api/, wires it to an existing use case via resolve(), handles the canonical error-to-HTTP mapping, and keeps presentation thin. Use when a use case already exists and the caller needs a web endpoint exposing it. Does NOT create the use case, does NOT…
completion-judge
Independently judge wide/approved work against the request, durable state, full diff, and fresh evidence; return PASS, CONTINUE, or BLOCKED with exact gaps. Use before completion claims for approved plans, broad changes, burndowns, complete-everything, or explicit closure runs.
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.
context
Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.
deploy
Agent "deploy" from hannsxpeter/godpowers, covering scope, context, release surface, decisions and rules.