Is sf-inspect safe to install?

SaferSkills independently audited sf-inspect (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

skills/sf-inspect/SKILL.md · 1 file

skills/sf-inspect/SKILL.md5.2 KB · Markdown

name: sf-inspect

description: Pull a complete structured dossier on a single prediction-market ticker. Use this skill when an agent has a specific ticker (e.g., KXRATECUT-26DEC31) and needs full context — market metadata, prices, liquidity, indicators, regime state, cross-venue counterpart, related markets, and follow-up actions — in one structured response.

license: CC-BY-4.0

metadata:

author: simplefunctions

version: "1.0.0"

SimpleFunctions Ticker Inspection

When to use

An agent has a specific ticker and needs full context
Before recommending a trade — verify liquidity, regime, indicators
After sf discover or sf research surfaces a candidate
When analyzing a thesis-linked market

Prerequisites

npm install -g @spfunctions/cli

No auth required. The sf inspect command and the underlying /api/agent/inspect/{ticker} endpoint are public.

Instructions

Step 1: Pull the dossier

sf inspect <ticker> --json

Examples:

sf inspect KXRATECUT-26DEC31 --json
sf inspect 0x0e4a0c937b8934c2475613b6322b3f8edc8dedc24762e01e42b0e6f87424a089 --json  # Polymarket

Kalshi tickers: KX prefix, dashes separate parts (e.g., KXFED-27APR-T3.50). Polymarket tickers: 0x-prefixed condition IDs.

Step 2: Read the structure

The response has these top-level fields:

Field	Use
`ticker`, `venue`, `title`, `description`	Identity
`price`, `bestBid`, `bestAsk`, `spread`	Current pricing
`volume`, `volume24h`, `openInterest`	Liquidity
`status`	`active`, `closed`, `resolved`
`closeTime`	Settlement deadline
`indicators`	SF-computed metrics (see below)
`regime`	Regime label + confidence + freshness
`crossVenue`	Counterpart on the other venue (if pair exists)
`nextActions`	Pre-filled commands for follow-up

Step 3: Interpret the indicators

Indicator	What it means	Read
`tauDays`	Days to settlement	scaling factor for all yield calcs
`iyYes`, `iyNo`	Implied yield per side (annualized)	higher = more juice; compare across markets
`cri`	Calibration ratio	1.0 = neutral, >1 = market overpricing YES
`ee`	Expected edge	model's edge estimate; null if no thesis attached
`las`	Liquidity-adjusted spread	small = tight book; >0.3 = noisy
`vr`	Volume ratio (vs. baseline)	>1 = elevated; >3 = hot
`residualVr`	Volume above what regime predicts	>2σ = informed money; >5σ = strong signal
`overround`	Sum of complementary contract prices minus 1	>0.05 = inefficient pricing
`rv`	Realized volatility	bounded path-dependent measure
`iar`	Implied attention ratio	activity vs. peers in the same theme
`hasOrderbook`	Whether orderbook data is fresh	false = use bid/ask cautiously

Step 4: Check regime

"regime": {
  "score": 0.568,
  "label": "neutral" | "stale" | "fast-moving" | "noisy",
  "fresh": true | false,
  "computedAt": "..."
}

If fresh: false, the regime label may be outdated. Re-run after sf world --delta --json --since 1h.

Step 5: Check cross-venue counterpart (if exists)

"crossVenue": {
  "ticker": "...",
  "venue": "polymarket" | "kalshi",
  "price": 67,
  "delta": 5,
  "confidence": 0.85
}

If a counterpart exists with confidence ≥ 0.75 and |delta| ≥ 3¢, there may be a cross-venue arb. Verify with sf cross-venue --preset arb.

Step 6: Follow next actions

Each nextActions entry is a pre-filled command:

"nextActions": {
  "inspect": [{ "command": "GET /api/agent/inspect/<ticker>" }],
  "related": [{ "command": "GET /api/public/contagion?window=6h" }]
}

Use these for deeper investigation without manually constructing URLs.

Optional Step 7: Pull price history

curl "https://simplefunctions.dev/api/public/market/<ticker>/history?window=7d"

For trajectory analysis. Returns indicator history with timestamps, prices, deltas, and yield evolution.

Expected output shape

{
  "ticker": "KXRATECUT-26DEC31",
  "venue": "kalshi",
  "title": "...",
  "price": 72,
  "bestBid": 71,
  "bestAsk": 73,
  "spread": 2,
  "volume": 12500,
  "volume24h": 1840,
  "openInterest": 8200,
  "status": "active",
  "closeTime": "2026-12-31T...",
  "indicators": { ... },
  "regime": { ... },
  "crossVenue": { ... } | null,
  "nextActions": { ... },
  "pageUrl": "https://simplefunctions.dev/markets/...",
  "apiUrl": "https://simplefunctions.dev/api/public/market/..."
}

Errors and recovery

404 on ticker: verify ticker format. For Kalshi, lookup at sf scan --keyword "<title>" --json. For Polymarket, ensure 0x-prefixed condition ID.
`status: closed` or `resolved`: market settled. Use /api/public/market/<ticker>/history for post-mortem analysis.
Missing indicators: market may be too new or low-volume. Indicators recompute every 15 min via cron.

sf-research — topic research that surfaces tickers
sf-discover — quality-ranked opportunity list
sf-pre-trade-check — adversarial check before entry

Reference docs

<https://docs.simplefunctions.dev/api-reference/market-detail>
<https://docs.simplefunctions.dev/concepts/indicators>
<https://docs.simplefunctions.dev/concepts/regime>

sf-inspect— agent skill

Is sf-inspect safe to install?

SimpleFunctions Ticker Inspection

When to use

Prerequisites

Instructions

Step 1: Pull the dossier

Step 2: Read the structure

Step 3: Interpret the indicators

Step 4: Check regime

Step 5: Check cross-venue counterpart (if exists)

Step 6: Follow next actions

Optional Step 7: Pull price history

Expected output shape

Errors and recovery

Reference docs

Audit the pieces. Scan the whole. Decide.

Is sf-inspect safe to install?

SimpleFunctions Ticker Inspection

When to use

Prerequisites

Instructions

Step 1: Pull the dossier

Step 2: Read the structure

Step 3: Interpret the indicators

Step 4: Check regime

Step 5: Check cross-venue counterpart (if exists)

Step 6: Follow next actions

Optional Step 7: Pull price history

Expected output shape

Errors and recovery

Related skills

Reference docs

Audit the pieces. Scan the whole. Decide.