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 DataSift-Ty-Personal/SiftStack --skill caller-reputation-monitorgit clone --depth 1 https://github.com/DataSift-Ty-Personal/SiftStackWrote 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/datasift-ty-personal/siftstack/caller-reputation-monitor)<a href="https://agentmods.dev/skills/datasift-ty-personal/siftstack/caller-reputation-monitor"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/caller-reputation-monitor/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/datasift-ty-personal/siftstack/caller-reputation-monitor"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/caller-reputation-monitor.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 | $0.00131 | $0.01944 |
| Opus 5.5 | $0.00052 | $0.00778 |
| Sonnet 5.5 | $0.00026 | $0.00389 |
| Haiku 4.5 | $0.00013 | $0.00194 |
Grade A, and why
caller-reputation-monitor 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 2mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Caller ID Reputation Monitor
Keep the user's outbound dialing numbers (DIDs) out of carrier spam labels: register them (prevention), monitor them daily (detection), rest and remediate the ones that degrade (recovery). Built for SmrtPhone users doing REI cold calling, but the concepts apply to any dialer.
The core insight: carriers never tell you a number is flagged. The truest signal you can get for free is your OWN answer rate cratering on a specific number. This skill reads that straight from the user's SmrtPhone call log. No Telnyx account, no port, no monthly fee for the default setup.
What is in this skill
references/quick-start.md- the 15-minute setup guide. START HERE for a new user.references/registration-and-remediation.md- why numbers get flagged, the free registration walkthrough (Free Caller Registry), and the runbook for clearing a number that is flagged right now.references/reputation-workflow.md- the full design: signal layers, fusion rules, the number lifecycle state machine, data model.references/telnyx-api-contract.md- verified Telnyx endpoints and fields (only needed for the optional carrier-grade upgrade).references/methodology.md- the deep research behind the whole system (carrier analytics engines, STIR/SHAKEN, healthy call-behavior targets, sources).scripts/- the complete working monitor. Stdlib-only Python except the two Playwright helpers.
How the monitor works (know this before helping)
Two signal layers, fused as worst-of:
| Layer | Source | Signal | Cost |
|---|---|---|---|
| L1 own traffic (default) | SmrtPhone call log (smrtphone_cdr.py) |
per-number ASR, ALOC, short-call % over a trailing 7-day window | free |
| L2 carrier reputation (optional, OFF by default) | Telnyx Number Reputation + Remediation API | carrier-grade spam_risk / spam_category + auto-remediation | $100/mo + porting numbers to Telnyx |
L1 healthy targets (SmrtPhone's own published bands): ASR >= 30%, ALOC >= 30 seconds, short calls (under 6s) <= 15% of outbound. A breach makes a number at least Watch, never Flagged on L1 alone. Below 15 dials in the window the sample is too small and L1 abstains (protects warm-up numbers).
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/methodology.md 54 KB
- references/quick-start.md 6.4 KB
- references/registration-and-remediation.md 4.5 KB
- references/reputation-workflow.md 15 KB
- references/telnyx-api-contract.md 9.4 KB
- scripts/config/enterprise.example.json 1.8 KB
- scripts/config/numbers.example.json 1.5 KB
- scripts/config/thresholds.json 4.7 KB
- scripts/dashboard.py 15 KB runs code
- scripts/monitor_run.cmd 768 B runs code
- scripts/monitor.py 38 KB runs code
- scripts/pull_smrtphone_numbers.py 6.3 KB runs code
- scripts/smrtphone_cdr.py 8.5 KB runs code
- scripts/smrtphone_login.py 2.6 KB runs code
- scripts/telnyx_cdr.py 11 KB runs code
- scripts/telnyx_reputation.py 13 KB runs code
- scripts/telnyx_setup.py 11 KB runs code
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.
- 2mo ago First seen · 80 lines · 131 tokens per session scan A 9673f735b4d3
caller-reputation-monitor is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (23 stars, last pushed 23d ago), licensed MIT. It adds 131 tokens to every session and 1,944 once invoked, about $0.0005 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 2026-08-30.
caller-reputation-monitor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| caller-reputation-monitorDataSift-Ty-Personal/SiftStack | Skill | 23 | 23d ago | MIT | A | 131 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |