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/tracer-cloud/opensre/posthog-summarynpx skills add Tracer-Cloud/opensre --skill posthog-summarygit clone --depth 1 https://github.com/Tracer-Cloud/opensreWrote 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/tracer-cloud/opensre/posthog-summary)<a href="https://agentmods.dev/skills/tracer-cloud/opensre/posthog-summary"><img src="https://agentmods.dev/badge/skills/tracer-cloud/opensre/posthog-summary.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00049 | $0.01192 |
| Opus 5 | $0.00024 | $0.00596 |
| Sonnet 5 | $0.00010 | $0.00238 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
posthog-summary scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PostHog Summary
PostHog product-analytics reporting for chat delivery. Produce a per-metric pulse over a window — what moved, why it matters — not a raw dashboard export. Single source (PostHog MCP); finish here, then optionally suggest a multi-source follow-up.
Requires the PostHog MCP integration (posthog_mcp). The REST-only
posthog integration cannot serve this skill.
1. Discover
list_posthog_tools once with name_filter: "insights dashboard sql events" to
find the query surface. Then call read-data-schema (or the equivalent schema
tool) BEFORE any aggregation query and only reference events and properties it
confirms exist. Do not reference a property (e.g. properties.$mcp_error)
without seeing it in the schema first — HogQL rejects queries against unknown
properties. To pull metric data, use call_posthog_tool with
tool_name: "execute-sql" and SQL as a top-level string:
{
"tool_name": "execute-sql",
"arguments": { "query": "SELECT count() FROM events WHERE event = '$pageview'" }
}
Never nest the SQL ({"query": {"query": "SELECT …"}}) — PostHog rejects that
with parameter "query" must be of type string. Use insight/dashboard tools
when the user names a specific dashboard.
2. Fetch metrics
Map user words to windows:
- 24h — "today", "overnight", morning report
- 7d — "this week", default weekly report
- 30d — "this month", monthly rollup
Run one small HogQL query per metric — do NOT combine multiple metrics into a
single aggregated statement, and never cross-join events against synthetic
"window" rows. That combined shape is the most common cause of PostHog's
unknown error running this query. Return only aggregate numbers (two
columns: current / previous) — never event-level rows. Compute the two windows
with an explicit conditional aggregate over a single time filter, e.g.:
SELECT
countIf(timestamp >= now() - INTERVAL 7 DAY) AS current,
countIf(timestamp >= now() - INTERVAL 14 DAY
AND timestamp < now() - INTERVAL 7 DAY) AS previous
FROM events
WHERE event = '$pageview'
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.
- 4d ago First seen · 113 lines · 49 tokens per session scan A 5169825939b2
posthog-summary is a skill published in the GitHub repository Tracer-Cloud/opensre (10,999 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 1,192 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 2026-08-30.
Other skills, from other repositories
host_bash
设备上跑只读 shell 命令做诊断探索(沙箱化 / read-only policy).
host_restart_service
重启允许列表内的 systemd service(mutating,触发 reviewer 二审).
file_inspector
Inspect files on the host filesystem.
edge_disk_audit
Audit disk usage on edge devices.
hello-world
Skill whose name uses a dash, expected to be normalized.
future_skill
A skill that uses fields ongrid does not yet recognize.