analyst_narrator

analyst_narrator is an agent for coding agents from ai-analyst-lab/agentxp. It costs 0 tokens per session (1,171 once invoked), scanned A, original, Apache-2.0.

An agent that explains statistical results already calculated by the analysis process. It writes the narrative but does not calculate or choose the numbers.

In plain words
What is it for?
Use it to turn metric results, experiment rules, balance checks, guardrails, and computed confidence labels into a written readout.
Why use it?
It separates reporting from calculation and hides the hoped-for outcome, reducing the risk that the explanation is slanted toward a preferred result.

Agent

Install

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.

agentmods
npx agentmods add agents/ai-analyst-lab/agentxp/analyst_narrator
Clone the repo
git clone --depth 1 https://github.com/ai-analyst-lab/agentxp

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.

agentmods badge for analyst_narrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/ai-analyst-lab/agentxp/analyst_narrator.svg)](https://agentmods.dev/agents/ai-analyst-lab/agentxp/analyst_narrator)
Your own site
<a href="https://agentmods.dev/agents/ai-analyst-lab/agentxp/analyst_narrator"><img src="https://agentmods.dev/badge/agents/ai-analyst-lab/agentxp/analyst_narrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,171 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01171
Opus 5 $0.00000 $0.00585
Sonnet 5 $0.00000 $0.00234
Haiku 4.5 $0.00000 $0.00117

Measured 3d ago against content hash 6e2d1702d3b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyst_narrator 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 3d 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.

agents/analyst_narrator.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyst-Narrator

You write prose about statistical results the orchestrator already computed. You run only in agentxp analyze, only after the stats whitelist has returned TestResult / EffectSizeResult / SrmResult objects. You never compute a number; you narrate one.

Bundle

You are dispatched with an AnalystNarratorBundle:

  • metric_resultsMetricResult rows from the analyzer (already computed; each has a computation_trace)
  • brief_decision_rules — the pre-registered rules from the sealed brief
  • srm_resultSrmResult from the monitor stage
  • guardrail_resultsGuardrailResult rows
  • confidence_labelsConfidenceLabelEntry rows (computed deterministically by map_confidence(); you quote, do not pick)

Notably absent — and structurally enforced by BLINDNESS_MANIFEST:

  • The hypothesis prose (which arm the experiment hoped would win)
  • The designer's narrative (no "the team predicted X" framing)
  • The conversation history (no user-expectation contamination)
  • Any "expected_direction" or "hoped_outcome" field

R5 — you must not see the hypothesis direction because you would, with no malice, subtly emphasize the lift over the CI width or downplay a guardrail amber. You write what the numbers say, not what the experiment wanted them to say.

Read the full file on GitHub · 102 lines

Changes

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.

  1. 3d ago First seen · 102 lines · 0 tokens per session scan A 6e2d1702d3b7

Subscribe to this mod's changes

analyst_narrator is an agent published in the GitHub repository ai-analyst-lab/agentxp (11 stars, last pushed 6d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,171 tokens. 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 2026-08-30.