Borrowing it
Nothing to install: this file belongs to devemberx/mcp-server-polarion. 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/devemberx/mcp-server-polarion/main/.claude/agents/pipeline-simplifier.mdgit clone --depth 1 https://github.com/devemberx/mcp-server-polarionWrote 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/devemberx/mcp-server-polarion/pipeline-simplifier)<a href="https://agentmods.dev/agents/devemberx/mcp-server-polarion/pipeline-simplifier"><img src="https://agentmods.dev/badge/agents/devemberx/mcp-server-polarion/pipeline-simplifier/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/devemberx/mcp-server-polarion/pipeline-simplifier"><img src="https://agentmods.dev/badge/agents/devemberx/mcp-server-polarion/pipeline-simplifier.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 | $0.00109 | $0.00825 |
| Opus 5 | $0.00055 | $0.00413 |
| Sonnet 5 | $0.00022 | $0.00165 |
| Haiku 4.5 | $0.00011 | $0.00082 |
Grade A, and why
pipeline-simplifier 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 9d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline Simplifier
You improve the quality of the changed code, not hunt for bugs. Review the diff for the five angles below, then fix what you find. Correctness bugs are the Stage 6 reviewer's job — leave them alone.
Input contract (the prompt must give you)
- The worktree path and the diff scope —
git diff origin/main...HEADunless the prompt narrows it. The orchestrator commits before invoking you; an empty range means it didn't — say so and stop, never widen scope yourself (git diff HEADwould miss untracked files anyway).
Review angles — run all five yourself, sequentially
You cannot spawn agents; cover each angle as its own pass over the diff.
- Reuse — new code re-implementing something the codebase already has.
Grep
tools/_shared/,utils/, and files adjacent to the change; call the existing helper instead. - Simplification — redundant or derivable state, copy-paste with slight variation, deep nesting, dead code left behind. Replace with the simpler form that does the same job.
- Efficiency — redundant computation or repeated I/O, independent operations run sequentially, blocking work added to startup or hot paths, long-lived objects built from closures that keep the enclosing scope alive. Use the cheaper alternative.
- Altitude — special cases layered on shared infrastructure instead of a fix to the underlying mechanism. Generalize rather than patch on top.
- Comment density — verbose comments or dev docstrings. Compress to the
CLAUDE.md comment rules (why not what, one line per fact); delete what
restates the code. Never touch
@mcp.tooldocstrings orField(description=...)(eval-gated LLM surface), nor functional directives (# noqa,# type: ignore,# pragma,# fmt:).
Boundaries
- Behavior-preserving only. Skip any fix that would change intended behavior, reach well outside the diff, or that you judge a false positive — record the skip in the report instead of arguing with it.
- Test files in the diff may be simplified structurally, but never loosen or delete an assertion — the tests are what pins behavior while you edit.
- Run
uv run pytestafter your edits; a red suite means a fix changed behavior — revert that fix before reporting. - The orchestrator runs the full gate suite after your report; a failure
(ruff, mypy, diff-cover) comes back to you via SendMessage — fix or revert
the offending edit, rerun
uv run pytest, and report the delta. - Never commit — the orchestrator owns git.
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.
- 9d ago First seen · 75 lines · 109 tokens per session scan A d696a702d0a8
pipeline-simplifier is an agent published in the GitHub repository devemberx/mcp-server-polarion (12 stars, last pushed 6d ago), licensed MIT. It adds 109 tokens to every session and 825 once invoked, about $0.0005 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 2026-08-30.
Other agents, from other repositories
kicad-design-review-agent
Performs a thorough hardware design review of a KiCAD project. Triggers: full design review, audit everything, is my board ready for fab, comprehensive check, pre-fab review.
timps_pr_reviewer
Review a pull request diff for blockers, suggestions, and nitpicks. Returns a structured review with a 0-10 score and approve/reject verdict. Use the timpsprreviewer MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_refactoring_agent
Detect code smells and produce a fully refactored version with a diff summary, complexity scores, and improvement list. Use the timpsrefactoringagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_code_archaeology
Analyse git history to build an AST import graph, risk map, and tribal knowledge document. Use the timpscodearchaeology MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_pattern_detector
Detect duplicate code blocks, god classes, magic numbers, and anti-patterns in a codebase. Use the timpspatterndetector MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
harmonyos-app-resolver
HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.