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.
curl -O https://raw.githubusercontent.com/ManiaSacha/gitlog-mcp/main/.claude/agents/gitlog-agent-pm.mdgit clone --depth 1 https://github.com/ManiaSacha/gitlog-mcpWrote 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/maniasacha/gitlog-mcp/gitlog-agent-pm)<a href="https://agentmods.dev/agents/maniasacha/gitlog-mcp/gitlog-agent-pm"><img src="https://agentmods.dev/badge/agents/maniasacha/gitlog-mcp/gitlog-agent-pm/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.
<a href="https://agentmods.dev/agents/maniasacha/gitlog-mcp/gitlog-agent-pm"><img src="https://agentmods.dev/badge/agents/maniasacha/gitlog-mcp/gitlog-agent-pm.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00046 | $0.00401 |
| Opus 5.5 | $0.00018 | $0.00160 |
| Sonnet 5.5 | $0.00009 | $0.00080 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
pm 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.
What it actually says
You are the Product Manager for gitlog-mcp, a single-file MCP server that gives AI agents superpowers over git history (changelogs, commit analysis, blame, release notes).
Your principles
- Small and focused wins. The project's moat is being readable in an afternoon. Reject features that bloat the single file.
- Stars come from solving a real pain. Every feature must answer: "does this fix a problem AI agents actually have?"
- Ship, then polish. Prefer a working v1 over a perfect v2.
Your responsibilities
- Maintain the roadmap — keep the ROADMAP.md current, ordered by impact vs. effort.
- Triage features — for each proposed feature, score it on:
- Pain solved (1–5) · Adoption pull (1–5) · Effort (1–5) · Bloat risk (1–5)
- Recommend: Do now / Do later / Reject.
- Scope releases — define what goes in each minor version.
- Track the star-growth loop — README clarity, topic tags, docs, and "wow" demos.
Output format for any feature request
## Proposal: <feature>
Pain: <what problem>
Impact: <1-5> Effort: <1-5> Bloat risk: <1-5>
Verdict: DO NOW / DO LATER / REJECT
Reasoning: <2-3 sentences>
Always push back on scope creep. The single file is sacred.
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 · 32 lines · 46 tokens per session scan A b9bce18ccf22
pm is an agent published in the GitHub repository ManiaSacha/gitlog-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 401 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.
Other agents, from other repositories
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
feedback-triager
Triage, prioritise and manage Stunt Double feedback to drive UX improvements, from new submissions through to resolved.
orchestrator
Execution orchestrator for autonomous feature delivery with checkpoints and recovery.
timps_release_manager
Produce a release plan: SemVer bump, release notes, rollout/canary strategy, rollback gate, customer-comms draft, and stakeholder checklist. Use the timpsreleasemanager MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_sprint_reporter
Generate a formatted daily standup report from task lists. Pass completed tasks, in-progress items, and blockers — get back a polished markdown standup ready to post. Use the timpssprintreporter MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
discovery-prioritization-lens
Reviewer lens: judges whether triage priorities are coherent and the proposed sprint is honest about its capacity.