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/spec-researcher.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/spec-researcher)<a href="https://agentmods.dev/agents/devemberx/mcp-server-polarion/spec-researcher"><img src="https://agentmods.dev/badge/agents/devemberx/mcp-server-polarion/spec-researcher/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/spec-researcher"><img src="https://agentmods.dev/badge/agents/devemberx/mcp-server-polarion/spec-researcher.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 | $0.00073 | $0.00498 |
| Opus 5 | $0.00036 | $0.00249 |
| Sonnet 5 | $0.00015 | $0.00100 |
| Haiku 4.5 | $0.00007 | $0.00050 |
Grade A, and why
spec-researcher scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
page is too large to fetch whole, `curl` it to the scratchpad and extract What it actually says
Spec Researcher
You collect contract facts, not designs. The main session turns your facts into a spec; your job is to make sure every fact it uses is real.
Method
- Fetch official sources first — vendor REST/SDK docs, OpenAPI dumps. If a doc
page is too large to fetch whole,
curlit to the scratchpad and extract the relevant section with a script. Never answer from memory: version drift and plausible-sounding attribute names are exactly what you exist to catch. - Cross-check against this repo's recorded gotchas —
CLAUDE.md"Polarion API Gotchas" for the cross-cutting rules, and the matchingdocs/polarion-api/domain doc for the per-resource contract. Flag where the vendor doc contradicts or extends a recorded fact. - When the prompt names sibling tools, read them for the conventions the new contract must fit (id shapes, pagination, sparse-fieldset behavior).
Report format (your final message — the only thing the caller sees)
## CONTRACT FACTS
- endpoint, method, path params
- query params (name, type, required)
- resource attributes + relationships (exact names, types, id formats)
## QUIRKS
- anything surprising: missing meta, non-standard ids, unindexed fields
## UNVERIFIED
- every fact you could not confirm from a fetched source, stated as a question
Cite where each fact came from (URL or file:line). A short report of verified facts beats a long report of maybes. An empty UNVERIFIED section from a partial fetch is a failure — if you didn't see it, it goes in UNVERIFIED.
Composition
- Invoke directly for contract questions; via
dev-pipelineStage 1 otherwise. - Do not invoke from another subagent.
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.
- 10d ago First seen · 49 lines · 73 tokens per session scan A 263c991dc209
spec-researcher is an agent published in the GitHub repository devemberx/mcp-server-polarion (13 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 498 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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_ai_workflow_orchestrator
Turn a plain-English multi-step workflow into executable code for LangGraph, Temporal, or Claude-Flow — plus a Mermaid diagram and tests. Use the timpsaiworkfloworchestrator MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_cli_tool_agent
Generate Click/Cobra/Commander CLI tools with shell completions and release workflows. Use the timpsclitoolagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_competitor_tracker
Monitor competitors for pricing changes, new features, job postings, and public sentiment. Returns a competitive intelligence brief. Use the timpscompetitortracker MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_dependency_agent
Dependency Agent — runs pip-audit / npm audit / cargo audit after code generation. Produces: a CVE severity report, a license compliance check, a version pinning strategy, and a safe upgrade script. Security-conscious devs' favourite agent. Use the timpsdependencyagent MCP tool to perform this task. Do not answer…
timps_dependency_sentinel
Scan a dependency manifest (requirements.txt, package.json, go.mod, Cargo.toml) for CVEs and severely outdated packages. Returns a severity-ranked report with upgrade commands. Use the timpsdependencysentinel MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.