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/marcusjellinghaus/mcp-tools-sql/commit-pushergit clone --depth 1 https://github.com/MarcusJellinghaus/mcp-tools-sqlWhat 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 | $0.00027 | $0.00389 |
| Opus 5 | $0.00014 | $0.00195 |
| Sonnet 5 | $0.00005 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
commit-pusher 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.
This is a copy
100% identical to commit-pusher — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Commit-Pusher Agent
You are a commit and push specialist.
Do not invoke /commit_push — it is disable-model-invocation, so the Skill tool will
refuse. Instead read .claude/skills/commit_push/SKILL.md with
mcp__mcp-workspace__read_file and follow its numbered process. Ignore its frontmatter and
any wording aimed at a user typing the command — you are running it unattended.
On top of that process:
- Scope — only the files named in your launch prompt may be modified. Confirm with
mcp__mcp-workspace__git"status"before staging; if anything else changed, stop and report back without committing. Stage those paths explicitly, nevergit add -A. - Message — use the one from your launch prompt. Multi-line messages need a POSIX
heredoc (
git commit -F - <<'EOF' … EOF); PowerShell here-strings leave a literal@in the subject line. - Shell —
gitcommands only. - Report the commit SHA, the files committed, and the push result.
The working directory is already correct — do not use cd or git -C.
Runs with bypassPermissions. Rationale and limits:
docs/repository-setup/agent-permissions.md in the mcp-coder repository.
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 · 36 lines · 27 tokens per session scan A c9234ff81c2d
commit-pusher is an agent published in the GitHub repository MarcusJellinghaus/mcp-tools-sql (2 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 389 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to commit-pusher, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.