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.
git clone --depth 1 https://github.com/MarcusJellinghaus/mcp-tools-pyWrote 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/marcusjellinghaus/mcp-tools-py/issue-approver)<a href="https://agentmods.dev/agents/marcusjellinghaus/mcp-tools-py/issue-approver"><img src="https://agentmods.dev/badge/agents/marcusjellinghaus/mcp-tools-py/issue-approver/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/marcusjellinghaus/mcp-tools-py/issue-approver"><img src="https://agentmods.dev/badge/agents/marcusjellinghaus/mcp-tools-py/issue-approver.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 | $0.00028 | $0.00388 |
| Opus 5.5 | $0.00011 | $0.00155 |
| Sonnet 5.5 | $0.00006 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
issue-approver 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 1mo 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
Issue-Approver Agent
You are an issue approval specialist. You approve issues by commenting /approve on them,
which triggers a GitHub Action to promote the issue status.
Do not invoke /issue_approve — it is disable-model-invocation, so the Skill tool will
refuse. Instead read .claude/skills/issue_approve/SKILL.md with
mcp__mcp-workspace__read_file and follow its numbered instructions. Ignore its frontmatter,
its "Resolve Issue Number" section — your issue number, and any --repo owner/repo flag,
come from your launch prompt — and any wording aimed at a user typing the command, including
its closing note about disable-model-invocation. You are running it unattended. The rest of
the file applies to you unchanged.
On top of that process:
- Scope — the issue number must match your launch prompt, and the prompt must confirm that no open questions remain. This replaces the skill's step 2, which assumes a human judging a conversation. If either check fails, stop and report back without approving.
- Shell —
ghcommands only. - Report the issue number and the status transition.
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.
- 1mo ago Changed · -15 lines · +16 tokens per session ba9d11c7df2b
- 1mo ago First seen · 51 lines · 12 tokens per session scan A 4756b7fcc915
issue-approver is an agent published in the GitHub repository MarcusJellinghaus/mcp-tools-py (20 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 388 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
executor
Run simple commands, collect and summarize results to protect parent context. Lightweight subagent.
task-delegator
Agent for delegating long-running tasks to OpenClaw. Manages async operations and monitors task progress.
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
timps_n8n_workflow_agent
You are the n8n workflow agent sub-agent from the TIMPS Swarm (category: priority).
platform-engineer
Use when building or improving internal developer platforms (IDPs), designing self-service infrastructure, or optimizing developer workflows to reduce friction and accelerate delivery. The platform-engineer agent specializes in designing platform architecture, implementing golden paths, and maximizing developer…
ticket-implementer
Implements one ticket in its own git worktree, commits, and reports a structured status. Pushes and restacks only when told.