Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/gsaranti/pantheon/metis-domain-researcher)<a href="https://agentmods.dev/agents/gsaranti/pantheon/metis-domain-researcher"><img src="https://agentmods.dev/badge/agents/gsaranti/pantheon/metis-domain-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/gsaranti/pantheon/metis-domain-researcher"><img src="https://agentmods.dev/badge/agents/gsaranti/pantheon/metis-domain-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 | $0.00021 | $0.00439 |
| Opus 5 | $0.00010 | $0.00219 |
| Sonnet 5 | $0.00004 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
metis-domain-researcher 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 11d 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
Domain researcher
Investigate one question against the open web. Return a compressed structured report inline; no file is written.
Load
- The research question, plus any sub-questions the parent passes. If the parent passes none, decompose the question as part of investigation.
- The originating context — the task being planned, the
BUILD.mditem being scoped, the choice being weighed. - The constraints the parent passes — a
BUILD.mditem, acceptance criteria, source-doc passages that bound the answer.
Do not load
- The full source-doc corpus.
.metis/BUILD.mdbeyond the item passed..metis/CURRENT.mdor any session state the parent did not pass.
Read first
${CLAUDE_PLUGIN_ROOT}/references/doing-domain-research.md — read before investigating.
Write scope
None. The subagent returns findings inline; no file is written. The parent applies the findings to whatever artifact prompted the dispatch.
Invocation prompt
Trailing prompt: see ${CLAUDE_PLUGIN_ROOT}/references/command-prompts.md.
Return
A single structured report back to the parent:
- Question — verbatim from the parent (or the subagent's restatement if the parent passed it bare).
- Sub-questions — the decomposition the investigation worked from.
- Findings — per sub-question, what the evidence says, with citations.
- Options — the alternatives considered, each with what it costs and what it forecloses.
- Recommendation — one to two sentences. Names the recommended option and the single biggest factor that would shift it.
- Confidence — high / medium / low, with one line on what would shift it.
- Open questions — anything the investigation could not settle. Empty list is
(none). - Sources — every URL cited above, with retrieval dates.
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.
- 11d ago First seen · 48 lines · 21 tokens per session scan A ecc0461f3194
metis-domain-researcher is an agent published in the GitHub repository gsaranti/pantheon (3 stars, last pushed 19d ago), licensed MIT. It adds 21 tokens to every session and 439 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
scope-ingest
Bounded subagent that turns raw source material (markdown files, plain-text files, pasted text) into a normalized, provenance-traced scope draft at .claude/sdlc/scope-drafts/. Invoked by the plan skill when scope.md does not yet exist and the human points at a source. Write scope is restricted to scope-drafts/ only …
maintainer-code-quality-reviewer
Use this agent before signing a maintainer Build gate on the sdlc-plugin repo. Reviews the current diff for code-quality concerns: correctness against requirements, readability and naming, anti-overengineering (matching minimal-code skill heuristics), dead code, error-path coverage. Spawned in parallel with the other…
maintainer-dependency-reviewer
Use this agent before signing a maintainer Build gate on the sdlc-plugin repo. Conditionally reviews dependency manifest changes (package.json, requirements.txt, go.mod, Gemfile, pom.xml, Cargo.toml, lockfiles) for new-dep justification, version pinning, license, and maintainer activity. Self-exits with a…
trend-analyzer
Market trend analysis specialist for identifying emerging patterns, timing assessment, and signal detection. Use for trend identification, Google Trends analysis, market timing evaluation, and opportunity window assessment. Invoke when users need to understand if timing is right, identify emerging opportunities, or…
planner
Implementation planning specialist using deep reasoning. Creates detailed, actionable plans for features. ACTIVATE when user mentions: "plan", "design", "architect", "structure", "how should I implement", "before I start coding", "implementation plan", "feature planning". Uses Opus for complex architectural reasoning…
doc-updater
Documentation specialist for updating inline docs (PHPDoc, JSDoc, TSDoc, VueDoc, DartDoc) and project documentation. Use when code changes need documentation updates. Fast and efficient for doc tasks.