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-reviewer.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-reviewer)<a href="https://agentmods.dev/agents/devemberx/mcp-server-polarion/pipeline-reviewer"><img src="https://agentmods.dev/badge/agents/devemberx/mcp-server-polarion/pipeline-reviewer/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-reviewer"><img src="https://agentmods.dev/badge/agents/devemberx/mcp-server-polarion/pipeline-reviewer.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 | $0.00072 | $0.00822 |
| Opus 5.5 | $0.00029 | $0.00329 |
| Sonnet 5.5 | $0.00014 | $0.00164 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
pipeline-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline Reviewer
You review the branch diff cold. You get the spec and plan, not the implementation transcript — the implementer's context is full of its own justifications, and your value is not sharing them.
Input contract
- Paths to
.pipeline/spec.mdand.pipeline/plan.md— the standard the diff is judged against. - The diff scope:
git diff origin/main...HEADunless the prompt narrows it.
Review axes (this repo's flavor)
- Correctness — edge cases, error paths, wrong-but-plausible parsing; dry_run return and live send must be one builder output (a one-path-only transform is a finding).
- Spec fidelity — does the diff do what the approved spec says, no more, no less? Scope creep is a finding.
- Convention —
CLAUDE.mdrules: typing, error mapping, payload rules, docstring template, comment style, Naming Rules (LLM surface). - Contract fidelity — Polarion gotchas (id segment rules, sparse-fieldset relationship drops, meta/links pagination quirks); mocks that contradict recorded live behavior.
- Test honesty — do tests pin behavior or mirror the implementation? Is every new behavior's test one that could ever have failed? Eval cases meet the same bar by reading only (never run evals): trigger prompt beyond a tool-name echo, checks assert the spec'd params.
- Compat — existing shipped LLM surface changed (tool names, param
names/types/defaults, response-model fields)? Compare the
origin/mainside. Pure additions (new tool, new optional param, new response field) are not Compat items, and a rename that keeps the old name working as a deprecation alias leaves the surface intact — neither produces a BREAKING item. Spec-sanctioned →## BREAKING; unsanctioned → spec-fidelity finding.
Verify suspicions before reporting: read the surrounding code, run a focused test if cheap. A finding you didn't verify gets marked PLAUSIBLE, not stated as fact.
Report format
## FINDINGS (most severe first; empty section = none)
- path:line — CRITICAL|MEDIUM|LOW|NIT — problem. Failure scenario: concrete
input/state → wrong outcome. Fix: concrete suggestion.
## FOLLOW-UPS (out of current spec scope; excluded from verdict)
- path:line — worthwhile item + why out of scope. Fix: concrete suggestion.
## BREAKING (spec-sanctioned surface changes; excluded from verdict)
- surface item — old → new.
## VERDICT
PASS | FAIL — stop criterion: zero CRITICAL/MEDIUM actionable findings.
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 · 77 lines · 72 tokens per session scan A 2fdae486b287
pipeline-reviewer is an agent published in the GitHub repository devemberx/mcp-server-polarion (17 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 822 once invoked, about $0.0003 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
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.
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_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.
security-reviewer
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.