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/posteyai/skills/postey-analyticsnpx skills add posteyai/skills --skill postey-analyticsgit clone --depth 1 https://github.com/posteyai/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/posteyai/skills/postey-analytics)<a href="https://agentmods.dev/skills/posteyai/skills/postey-analytics"><img src="https://agentmods.dev/badge/skills/posteyai/skills/postey-analytics.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 5.1 | $0.00048 | $0.01089 |
| Opus 5 | $0.00024 | $0.00544 |
| Sonnet 5 | $0.00010 | $0.00218 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
postey-analytics 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 6d 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.
Postey Analytics
Reading numbers is easy. Saying what they support, and refusing to say more, is the job.
Check the data is real before interpreting it
Do this first, every time. Platform analytics arrive partial, delayed, or absent, and a confident reading of a broken feed is worse than saying nothing.
| Symptom | What it means | What to say |
|---|---|---|
every metric is 0 across all posts on a platform |
the feed is not returning, or the platform never provided it | say the platform reports nothing; do not rank by it |
impressions present, engagement all 0 |
partial fetch | use impressions only, and name the limitation |
| one post has numbers, its siblings do not | the others have not been fetched yet | compare only the ones that have data |
fetch_count is 0 |
never collected | not "zero performance" — no data at all |
Zero is not a result. On a real account checked during development, every LinkedIn post reported zero impressions while the same content on X reported between 481 and 2,935. Ranking that account's LinkedIn posts would have produced a confident ordering of nothing.
What the numbers can and cannot support
They can support: this post got more reach than that one; this format appears more often near the top; this account's median engagement moved after a change.
They cannot support: why. Attribution needs a controlled comparison that social platforms do not give you. Say "these three of your top five were lists" — not "lists perform better for you", which is a causal claim from five data points.
Three traps worth naming out loud when they apply:
- Survivorship. Top posts are top by definition. Look at the bottom too, or every conclusion is "do more of what already worked".
- Sample size. Under ~10 posts with real data, report observations, not patterns.
- Time confounds. A post published during a spike in following did not earn that reach on content alone.
Turning it into a decision
The output is a recommendation the user can act on this week, with its evidence attached:
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.
- 6d ago First seen · 113 lines · 48 tokens per session scan A d3fa956dcf20
postey-analytics is a skill published in the GitHub repository posteyai/skills (5 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 1,089 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
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…
qmclaw-workbench
使用 OpenQuantum 的 QMClaw Local Tool 对超导量子比特 S21、能谱、Rabi、Ramsey、T1、SingleShot、DRAG、π 脉冲、功率偏移、Delta 和 RB 等 13 类测控实验做有界、确定性的本地模拟，并组织单比特调校工作流。用于实验规划、接口联调、教学和无硬件预检；不连接 LabRAD/lqms、真实仪器或量子云，不修改校准参数，也不替代 Scientific Validator。.
quick-capture
Use this skill to drop a new task into GSD Task Manager from any AI assistant that has the gsd-mcp-server connected.
xmemo-vscode
Use XMemo from VS Code (and forks like Cursor/Windsurf) to recall project context, capture engineering decisions, preserve handoff state, and connect to the hosted XMemo MCP endpoint safely.
event-staffing-ordering
Order W-2 event staff for US/CA events through TempGuru.