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 skills add Aditya923-c/xpoz-agent-skills --skill influencer-discoverygit clone --depth 1 https://github.com/Aditya923-c/xpoz-agent-skillsWrote 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/skills/aditya923-c/xpoz-agent-skills/influencer-discovery)<a href="https://agentmods.dev/skills/aditya923-c/xpoz-agent-skills/influencer-discovery"><img src="https://agentmods.dev/badge/skills/aditya923-c/xpoz-agent-skills/influencer-discovery/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/skills/aditya923-c/xpoz-agent-skills/influencer-discovery"><img src="https://agentmods.dev/badge/skills/aditya923-c/xpoz-agent-skills/influencer-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.03318 |
| Opus 5 | $0.00034 | $0.01659 |
| Sonnet 5 | $0.00014 | $0.00664 |
| Haiku 4.5 | $0.00007 | $0.00332 |
Grade A, and why
influencer-discovery scanned grade A with 2 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 12d 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.
import secrets, hashlib, base64, urllib.parse, json, urllib.request, os Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run(['mcporter', 'config', 'remove', 'xpoz'], capture_output=True) How it starts
The opening of the file, as written. The whole thing — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Influencer Discovery
Overview
Find, evaluate, and rank influencers for any niche across Twitter/X and Instagram. Identifies who is actively creating content about a topic, ranks them by engagement and relevance, and provides authenticity scoring.
When to Use
Activate when the user asks:
- "Find influencers in [NICHE] on Twitter"
- "Who are the top voices talking about [TOPIC]?"
- "Discover thought leaders in [INDUSTRY]"
- "Find micro-influencers for [PRODUCT CATEGORY]"
- "KOL research for [TOPIC]"
- "Who should we partner with for [CAMPAIGN]?"
Setup & Authentication
Before fetching data, ensure Xpoz access is configured. Follow these checks in order.
Check 1: Already authenticated?
If you have MCP tools, try calling any Xpoz tool (e.g., checkAccessKeyStatus). If it works → skip to Step 1.
If you have the SDK, try:
from xpoz import XpozClient
client = XpozClient() # reads XPOZ_API_KEY env var
If this succeeds without error → skip to Step 1.
If neither works, you need to authenticate. Choose the path that fits your environment:
Path A: MCP via mcporter (OpenClaw agents)
If mcporter is available:
mcporter call xpoz.checkAccessKeyStatus
If hasAccessKey: true → ready. If not:
mcporter config add xpoz https://mcp.xpoz.ai/mcp --auth oauth
Then authenticate — generate the OAuth URL and send it to the user:
Step 1: Generate authorization URL
import secrets, hashlib, base64, urllib.parse, json, urllib.request, os
verifier = secrets.token_urlsafe(64)
challenge = base64.urlsafe_b64encode(hashlib.sha256(verifier.encode()).digest()).rstrip(b'=').decode()
state = secrets.token_urlsafe(32)
# Dynamic client registration
reg_req = urllib.request.Request(
'https://mcp.xpoz.ai/oauth/register',
data=json.dumps({
'client_name': 'Agent Skills',
'redirect_uris': ['https://www.xpoz.ai/oauth/openclaw'],
'grant_types': ['authorization_code'],
'response_types': ['code'],
'token_endpoint_auth_method': 'none',
}).encode(),
headers={'Content-Type': 'application/json'},
)
reg_resp = json.loads(urllib.request.urlopen(reg_req).read())
params = urllib.parse.urlencode({
'response_type': 'code',
'client_id': reg_resp['client_id'],
'code_challenge': challenge,
'code_challenge_method': 'S256',
'redirect_uri': 'https://www.xpoz.ai/oauth/openclaw',
'state': state,
'scope': 'mcp:tools',
'resource': 'https://mcp.xpoz.ai/',
})
auth_url = 'https://mcp.xpoz.ai/oauth/authorize?' + params
# Save state for token exchange
os.makedirs(os.path.expanduser('~/.cache/xpoz-oauth'), exist_ok=True)
with open(os.path.expanduser('~/.cache/xpoz-oauth/state.json'), 'w') as f:
json.dump({'verifier': verifier, 'state': state, 'client_id': reg_resp['client_id'],
'redirect_uri': 'https://www.xpoz.ai/oauth/openclaw'}, f)
print(auth_url)
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.
- 12d ago First seen · 403 lines · 68 tokens per session scan A 760b8aa110e7
influencer-discovery is a skill published in the GitHub repository Aditya923-c/xpoz-agent-skills (5 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 3,318 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
craft
Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…
pipeline
Use when the user asks to take a substantial feature from an initial idea through implementation in one mostly autonomous run.
bug-fix
Use when a bug, regression, or unexpected behaviour is reported and the user wants it fixed end to end — "why is X broken", "this stopped working after Y", "fix this crash". Also use when a symptom is known but its cause is not. Not for building new behaviour, and not for a change whose cause is already proven.
bug-investigate
Use when someone wants to know WHY something is broken and has not asked for it to be fixed — "why is this happening", "what's causing this error", "find out what's wrong", "diagnose this before we decide". Also use before committing to a fix, when the cause is unknown and the decision depends on it. Not for fixing …
setup
Use when superb's skills need their dependencies installed or checked — "set up superb", "install the dependencies", "why does pipeline say superpowers is missing", after a fresh plugin install, or on a new machine. Also use when a skill fails complaining that a superpowers sub-skill cannot be found.
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.