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 agentmods add skills/taboola/realize-claude-plugin/reportsnpx skills add taboola/realize-claude-plugin --skill reportsgit clone --depth 1 https://github.com/taboola/realize-claude-pluginWhat 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 | $0.00036 | $0.01542 |
| Opus 5 | $0.00018 | $0.00771 |
| Sonnet 5 | $0.00007 | $0.00308 |
| Haiku 4.5 | $0.00004 | $0.00154 |
Grade A, and why
reports 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 2d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reports
Wraps the four Realize MCP report tools. Reports return CSV, not JSON — interpret the output in prose rather than dumping it back at the user.
Prerequisites
account_idresolved via theaccountsskill.
Tools this skill wraps
| Tool | Sort | Filters | Good for |
|---|---|---|---|
mcp__realize-mcp__get_top_campaign_content_report |
✓ | — | "What content performed best?" |
mcp__realize-mcp__get_campaign_breakdown_report |
✓ | ✓ | "Break down campaign X by " |
mcp__realize-mcp__get_campaign_history_report |
— | — | "How did campaign X trend over time?" |
mcp__realize-mcp__get_campaign_site_day_breakdown_report |
✓ | ✓ | "Which sites/days drove the results?" |
Sort. sort_field is one of "clicks", "spent", "impressions". sort_direction is "ASC" or "DESC" (uppercase, default "DESC").
Filters. Named filters (plural). The parameter is a flat JSON object with string-only values that is merged into the upstream API's query string as-is. Example: {"campaign_status": "RUNNING", "region": "US"}. There is no predefined filter schema — keys and values are forwarded verbatim to the Realize API, and unknown keys are passed through without error on the MCP side. Nested objects and arrays are not accepted.
Dates. start_date and end_date are required on every report tool. Format: YYYY-MM-DD (ISO date, no time component, no timezone).
CSV output format
Every response starts with a report header and a metadata line prefixed with 📊:
🏆 **<Report Name> CSV** - Account: <account_id> | Period: <start_date> to <end_date>
📊 Records: 250 | Total: 1500 | Page: 1 | Size: 250
<csv header row>
<csv data rows...>
Always cite Total in your summary so the user knows the query's scope. If the response includes a ⚠️ **TRUNCATED** banner, surface it — the data you see is incomplete.
See references/csv-examples.md for concrete sample outputs and references/report-fields.md for what each report returns.
What ships with it
2 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.
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.
- 2d ago First seen · 101 lines · 36 tokens per session scan A 352f21ce3477
reports is a skill published in the GitHub repository taboola/realize-claude-plugin (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,542 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.