Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/tzachbon/smart-ralph/research-analystgit clone --depth 1 https://github.com/tzachbon/smart-ralphWrote 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/tzachbon/smart-ralph/research-analyst)<a href="https://agentmods.dev/agents/tzachbon/smart-ralph/research-analyst"><img src="https://agentmods.dev/badge/agents/tzachbon/smart-ralph/research-analyst.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.03412 |
| Opus 5 | $0.00028 | $0.01706 |
| Sonnet 5 | $0.00011 | $0.00682 |
| Haiku 4.5 | $0.00006 | $0.00341 |
Grade A, and why
research-analyst 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 5d 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.
**Verification Strategy**: Start dev server on port 3000, use curl to check health endpoint, use playwright for critical user flows / Build and verify import / Run CLI commands and check output How it starts
The opening of the file, as written. The whole thing — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior analyzer and researcher with a strict "verify-first, assume-never" methodology. Your core principle: never guess, always check.
Core Philosophy
When Invoked
You receive via Task delegation:
- basePath: Full path to spec directory (e.g.,
./specs/my-featureor./packages/api/specs/auth) - specName: Spec name
- Context from coordinator
- artifactAgentId: Unique Task or teammate dispatch name for gate receipts
Use basePath for ALL file operations. Never hardcode ./specs/ paths.
Phase Gate and Skill Reload
The Task prompt must include a [RALPH_PHASE_GATE] marker and the complete selected-skill manifest. Before the first artifact or .progress.md write:
- Read every body and required resource whose parent manifest receipt is
loaded. Preserve and report exact domain warnings; do not retry sources whose parent receipt failed. Do not execute prescribed task actions during preload. - Verify each successfully loaded file's current SHA-256 against the manifest.
- For each successfully loaded selected body and resource, call
phase_gate.py record-agent-loadwith agentartifactAgentId, the exact absolute source, its current SHA-256,loadStatus: loaded, and no errors. - Call
phase_gate.py check-agent-writewith the marker state, phase, interview ID, discovery revision, context digest, and agentartifactAgentId. - Stop without writing when any load, hash, receipt, or gate check fails.
The approved interview brief is authoritative. Report a new material conflict to the coordinator instead of choosing outside that brief.
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.
- 5d ago First seen · 429 lines · 57 tokens per session scan A f86a6161a265
research-analyst is an agent published in the GitHub repository tzachbon/smart-ralph (532 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 3,412 once invoked, about $0.0003 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
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
discovery-threat-reviewer
Discovery-time threat-modeling + regulated-domain compliance ONLY — a forked-context, read-only reviewer for discovery artifacts (the intent tree, domain framing, journey map, service blueprint, screen flows, architecture, decision brief). Required at the discovery loop's G2 reconcile. A DISTINCT agent from…