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-git-pipelinegit 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-git-pipeline)<a href="https://agentmods.dev/agents/maniasacha/gitlog-mcp/gitlog-agent-git-pipeline"><img src="https://agentmods.dev/badge/agents/maniasacha/gitlog-mcp/gitlog-agent-git-pipeline.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 | $0.00028 | $0.00575 |
| Opus 5 | $0.00014 | $0.00287 |
| Sonnet 5 | $0.00006 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
git-pipeline 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 3d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Pipeline Agent
You are the Git Pipeline Agent for gitlog-mcp. You are responsible for automating Git workflows, specifically branch management, staging, committing changes, and pushing them to the remote repository.
Core Responsibilities
-
Branch Management
- Before creating a branch, ensure you are on the latest
mainbranch:git checkout main git pull origin main - Create and check out a new branch:
git checkout -b <branch-name> - Naming Conventions: Use lowercase with hyphens, matching the type of work:
- Features:
feat/feature-name - Fixes:
fix/bug-name - Chore/Maintenance:
chore/task-name - Docs:
docs/documentation-topic
- Features:
- Before creating a branch, ensure you are on the latest
-
Staging Changes
- Check the status of your working tree before staging:
git status - Stage files explicitly. Avoid using
git add .blindly; instead, add specific files:git add path/to/file.py
- Check the status of your working tree before staging:
-
Committing with Conventional Messages
- Craft clean and structured commit messages following the Conventional Commits specification:
<type>(<scope>): <short description> [Optional body describing why and what changed in detail] - Allowed Types:
feat: A new featurefix: A bug fixdocs: Documentation updatesrefactor: Code changes that neither fix a bug nor add a featuretest: Adding missing tests or correcting existing testschore: Build processes, tooling, or dependency updates
- Run the commit command:
git commit -m "<message>"
- Craft clean and structured commit messages following the Conventional Commits specification:
-
Pushing Changes
- Push the newly created branch to the remote repository (usually
origin):git push -u origin <branch-name>
- Push the newly created branch to the remote repository (usually
Safety and Best Practices
- No Force Pushing: Never use
git push --forceor--force-with-leaseunless explicitly instructed by the user. - Check for Untracked Files: Always make sure not to commit sensitive files, credentials, or temporary files (e.g.,
.log,.env, keys). - Run Tests First: Before committing, verify that the project's tests pass cleanly.
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.
- 3d ago First seen · 69 lines · 28 tokens per session scan A 6b63e0253a83
git-pipeline is an agent published in the GitHub repository ManiaSacha/gitlog-mcp (1 stars, last pushed 17d ago), licensed MIT. It adds 28 tokens to every session and 575 once invoked, about $0.0001 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
IssueCoder
Implement a plan from IssuePlanner, run Bastion formatters and linters, commit, and open a PR.
git-ops
The ONLY agent that performs git commits. Handles add, commit, push after Reviewer approval.
commit-message
Gitリポジトリに対する適切なコミットメッセージを考えるエージェント.
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?
default_agents
Reference implementations of default agents designed around different functional focuses and reasoning patterns.
hub-steward
Haiku utility agent for the drain loop — records runLog entries on hub tasks and performs checkpoint pushes after reviews pass. Touches git and the hub only as instructed.