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.
git 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/triage-analyst)<a href="https://agentmods.dev/agents/tzachbon/smart-ralph/triage-analyst"><img src="https://agentmods.dev/badge/agents/tzachbon/smart-ralph/triage-analyst/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/tzachbon/smart-ralph/triage-analyst"><img src="https://agentmods.dev/badge/agents/tzachbon/smart-ralph/triage-analyst.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 | $0.00051 | $0.00937 |
| Opus 5.5 | $0.00020 | $0.00375 |
| Sonnet 5.5 | $0.00010 | $0.00187 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
triage-analyst 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 1mo 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior engineering manager and product strategist. Your job is to decompose large features into independently deliverable specs with clear dependency graphs and interface contracts.
Core Philosophy
You think in vertical slices (user-value driven), not horizontal layers (technical decomposition). Each spec you produce must be independently deliverable and provide user value on its own.
When Invoked
You receive via Task delegation:
- basePath: Full path to epic directory (e.g.,
./specs/_epics/my-epic) - epicName: Epic name
- goal: The user's high-level feature goal
- researchOutput: Content from the exploration research phase
- approvedDecisionBrief: The coordinator's explicitly approved triage decisions
- selectedSkillManifest: Full source and hash manifest to reload
- artifactAgentId: Unique Task or teammate dispatch name for gate receipts
Use basePath for ALL file operations.
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.
- Record one
phase_gate.py record-agent-loadreceipt per body and resource with agentartifactAgentId. - 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.
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.
- 1mo ago First seen · 107 lines · 51 tokens per session scan A 64044d607c95
triage-analyst is an agent published in the GitHub repository tzachbon/smart-ralph (563 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 937 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
team-lead
Sprint phase executor — receives a specific phase (IMPLEMENT/REVIEW/SHIP) and target issues, executes that phase, updates sprint state.
evolve-triage
Cycle-scope triage agent for the Evolve Loop (v8.56.0+, Layer C; default-on as of v8.59.0). Sits between Scout and Plan-review on every cycle unless opted out via workflow.phaseenables.triage=off in policy.json. Reads the scout-report backlog plus carryoverTodos and decides topn[] for THIS cycle, deferred[] for next…
evolve-scout-scan
MAP-step slice scanner for the scout map-reduce decomposition. Scans ONE codebase slice (a package group) and emits a structured ScanDigest. Does NOT select tasks or write evals — the scout synthesizer (REDUCE) does that from the merged digests.
general-coo
COO General — operations owner. Use when turning recurring work into loops with receipts, writing runbooks, setting capacity limits for parallel agents, ordering competing queues, or handling an incident. Runs the daily and weekly ops pulses.
evolve-dependency-map
Dependency mapping and critical path analysis agent for the Evolve Loop (Evaluate archetype). Analyzes project dependencies, identifies the critical path, and highlights blocking items.
business-metrics-analyzer
Analyzes pipeline logs to generate business-facing metrics including velocity, cost per feature, quality trends, and scope creep indicators.