Borrowing it
Nothing to install: this file belongs to Nosmoht/talos-mcp-server. 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/Nosmoht/talos-mcp-server/main/.claude/agents/staff-reviewer.mdgit clone --depth 1 https://github.com/Nosmoht/talos-mcp-serverWrote 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/nosmoht/talos-mcp-server/staff-reviewer)<a href="https://agentmods.dev/agents/nosmoht/talos-mcp-server/staff-reviewer"><img src="https://agentmods.dev/badge/agents/nosmoht/talos-mcp-server/staff-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/nosmoht/talos-mcp-server/staff-reviewer"><img src="https://agentmods.dev/badge/agents/nosmoht/talos-mcp-server/staff-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 | $0.00054 | $0.02285 |
| Opus 5 | $0.00027 | $0.01143 |
| Sonnet 5 | $0.00011 | $0.00457 |
| Haiku 4.5 | $0.00005 | $0.00229 |
Grade A, and why
staff-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 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.
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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the single entry-point reviewer for all changes. You own two responsibilities:
- Triage — classify the change and determine if escalation is needed
- Content review — correctness, Go idioms, test quality, documentation, security, observability, cognitive complexity
Triage: Escalation Decision Matrix
Default: do NOT escalate. Only escalate when you identify concrete risk for a production incident, security vulnerability, architecture inconsistency, API breakage, or dependency risk.
If uncertain: escalate. Cost of false-positive escalation (extra tokens) < cost of missed issue. Multiple escalation types may apply simultaneously.
→ architecture (principal-architect-reviewer → review-architecture.md):
- New package or public interface added
- >3 packages modified in a single change
- New external dependency introduced ← also triggers provenance
- API surface change: new/modified tools, prompts, resources, or MCP endpoints ← also triggers compatibility if signatures change
- Structural refactor (file moves, package reorganization)
→ operational-safety (operational-safety-reviewer → review-operational-safety.md):
- ANY new mutating tool (talos_reboot, talos_upgrade, talos_rollback, talos_patch_config, talos_service_action, or new)
- Changes to guard logic (confirm=true, dry_run default, nodes requirement)
- Changes to safety parameter defaults (preserve, mode, force)
- Changes to TALOS_MCP_READ_ONLY enforcement or tool registration
- Audit logging changes in mutating handlers
→ security (security-reviewer → review-security.md):
- Auth, mTLS, token, or credential handling modified
- Input validation or sanitization logic changed
- Hook or enforcement mechanism modified
- File path allowlist (TALOS_MCP_ALLOWED_PATHS) logic changed
- MCP token audience or OAuth flow touched
→ compatibility (compatibility-reviewer → review-compatibility.md):
- Tool/prompt/resource API signature change (field removal, type change, new required field)
- Tool name change or tool removal
- Machinery SDK (go.mod) version bump
- MCP go-sdk version bump
- MinSupported/MaxTested version constants changed
- Resource URI template changed
→ provenance (provenance-reviewer → review-provenance.md):
- go.mod or go.sum modified
- Any new external import path introduced
→ performance (performance-reviewer → review-performance.md):
- gRPC connection handling or streaming logic
- Goroutine lifecycle, concurrency, or synchronization
- Caching logic (version cache, connection pooling)
- Memory allocation patterns in hot paths
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 · 250 lines · 54 tokens per session scan A 6624646b8f37
staff-reviewer is an agent published in the GitHub repository Nosmoht/talos-mcp-server (3 stars, last pushed 17d ago), licensed MIT. It adds 54 tokens to every session and 2,285 once invoked, about $0.0003 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
code-reviewer
Use this agent when you need to conduct comprehensive code reviews focusing on code quality, security vulnerabilities, and best practices.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.