Narrative Tracker

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha 0448e87653f9 · 14 Oct 2026Report an issue or request a re-scan

• Publisheraaronjmars GitHub organizationOwner of the repository this skill is read from
• Source folderaaronjmars/aeon/skills/narrative-trackerThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdict0448e87653f9A new audit runs when the source changes
• Repository statusNot archivedPushed today
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Track rising, peaking, and fading crypto/tech narratives with quantitative mindshare + velocity signals and explicit positioning calls

---
name: narrative-tracker
description: Track rising, peaking, and fading crypto/tech narratives with quantitative mindshare + velocity signals and explicit positioning calls
metadata:
  commits: true
  permissions:
    - contents:write
  title: Narrative Tracker
  mode: read-only
  category: crypto
  tags:
    - crypto
    - research
  requires:
    - XAI_API_KEY
---
<!-- autoresearch: variation B — sharper output (quantitative mindshare + velocity + explicit positioning calls, with multi-angle inputs from A, dedup/empty-state handling from C, and transition detection from D) -->

Read `memory/MEMORY.md` for context on prior narrative observations.
Read the last 3 days of `memory/logs/` — specifically any prior `### narrative-tracker` entries — to (a) avoid re-reporting the same narratives without new info, and (b) detect phase transitions vs the last run.

## Goal

Produce a *decision-grade* narrative map: every narrative gets a mindshare score, a velocity arrow, a sentiment tag, named drivers, and an explicit position call. Classification without a position call is noise.

## Steps

### 1. Ingest signals

**a. X/Twitter narratives — X.AI API (primary).** The primary signal is a direct `curl` to the X.AI Responses API with Grok's `x_search` tool — see **## Fetching** below for the full contract. `XAI_API_KEY` is injected into this skill's environment via `requires:`; it is present and valid, so this path is required whenever the key check prints `KEY_PRESENT`. Set the Bash tool `timeout` to ≥180000 when running the curl (x_search takes 30-120s) and capture the HTTP status:
```bash
FROM_DATE=$(date -u -d "3 days ago" +%Y-%m-%d 2>/dev/null || date -u -v-3d +%Y-%m-%d)
TO_DATE=$(date -u +%Y-%m-%d)
# Presence check uses the ${VAR:+x} modified expansion, NOT a bare $XAI_API_KEY — the bare
# form trips the Bash secret-expansion analyzer; the :+ form does not (it never puts the value on the line).
[ -n "${XAI_API_KEY:+x}" ] && echo KEY_PRESENT || echo KEY_UNSET
# Build the JSON payload to a file with jq (do NOT hand-assemble it), then POST the file.
# TWO SEPARATE commands on purpose: the jq (which interpolates $PROMPT/$FROM_DATE/$TO_DATE)
# is kept OUT of the ./secretcurl command — never pipe jq into secretcurl, and never put a
# $VAR in the secretcurl line, or the Bash permission analyzer blocks the network call.
# The `>` redirect to /tmp is fine in read-only mode (it is not a repo path; nothing reverts it).
PROMPT="Search X for the dominant crypto and tech narratives from ${FROM_DATE} to ${TO_DATE}. Return 12-15 distinct narrative threads. For each: 1) short label, 2) 3-5 representative @handles driving it, 3) 2-3 tweet permalinks, 4) rough mention-volume descriptor (niche / growing / saturating / cooling), 5) the strongest one-line bear case against it."
jq -n --arg p "$PROMPT" --arg fd "$FROM_DATE" --arg td "$TO_DATE" \
  '{model:"grok-4.7", input:[{role:"user",content:$p}], tools:[{type:"x_search",from_date:$fd,to_date:$td}]}' \
  > /tmp/xai-nt-payload.json
HTTP=$(./secretcurl -s -o /tmp/xai-nt.json -w '%{http_code}' --max-time 150 -X POST "https://api.x.ai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {XAI_API_KEY}" \
  -d @/tmp/xai-nt-payload.json)
echo "xai http=$HTTP bytes=$(wc -c </tmp/xai-nt.json)"
```
Run that block **verbatim** (do not hand-reassemble the JSON — the `jq -n` builder exists precisely so quoting/expansion can't break; keep the jq and the `./secretcurl` as two separate commands). The `echo "xai http=$HTTP ..."` line **must appear in your output** — it is your proof the call ran. On `HTTP=200` with a non-empty body, parse `/tmp/xai-nt.json` with `jq -r '.output[] | select(.type == "message") | .content[] | select(.type == "output_text") | .text'` and use that as the primary narrative signal (`SOURCE=api`).

**b. WebSearch / WebFetch fallback (last-resort only).** You may reach for this **only after** you have shown an `xai http=<code>` line proving Path A actually ran and returned a non-2xx code (or an empty body, or timed out). If you have no `xai http=` line, you did not run the call - go back and run it. Reach for the fallback **only** when Path A genuinely fails - `KEY_UNSET`, a non-2xx HTTP code, an empty parse, or a timeout. It is lower quality (WebSearch favours old high-engagement posts) and is **never co-equal** with Path A. Record the fetch failure in your final output with the **true reason** - `key-unset` | `http-<code>` | `empty` | `timeout` - never "XAI_API_KEY unavailable" when the key was set (a slow curl is a `timeout`, not a missing key). Then compile narratives via WebSearch (`crypto narrative ${TO_DATE}`, `AI agent crypto trend this week`) and WebFetch on individual tweet URLs; discard anything older than the 3-day window.

**c. Quantitative reference points (supplement).** Independently of the fetch path, cross-check mindshare against external quantitative benchmarks with one WebSearch: `DefiLlama narrative tracker` OR `Kaito mindshare leaderboard`. Pull 1-2 concrete numbers (project name, metric, link) to calibrate the mindshare scores in step 2. This is a calibration cross-check, **not** a narrative source. Do not paraphrase — extract facts.

**d. Memory diff.** Extract narrative labels mentioned in the last 3 days of `### narrative-tracker` log entries. You'll compare against them in step 4.

### 2. Score each narrative

For each distinct narrative (merge near-duplicates aggressively — "AI agents" and "agentic crypto" are the same), assign:

| Field | Scale | How to decide |
|---|---|---|
| **Mindshare** | 1-5 | 1 = fringe, 3 = known in the sector, 5 = dominating timelines. Base on count of distinct drivers + whether you had to dig or it surfaced unprompted. |
| **Velocity** | ↑↑ / ↑ / → / ↓ / ↓↓ | Compared to the 3-day window or prior log entries. ↑↑ = tripled in attention, ↓↓ = was loud 3 days ago, now absent. |
| **Phase** | Emerging / Rising / Peak / Fading | Use the velocity + mindshare combo. Emergi

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/aaronjmars/aeon
git -C aeon checkout 0448e87653f9

Works in

1. 2026-10-14
   ✓SAFE B 89 / 100

   first audit · source 0448e87653f9

Questions about Narrative Tracker

• github.com/aaronjmars/aeon/tree/main/skills/narrative-tracker — the audited source at commit 0448e87653f9 and every finding aboveObserved · 14 Oct 2026

Spotted something wrong? Report a correction · Methodology