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 taosdata/agent-skills --skill idmp-analysisgit clone --depth 1 https://github.com/taosdata/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/taosdata/agent-skills/idmp-analysis)<a href="https://agentmods.dev/skills/taosdata/agent-skills/idmp-analysis"><img src="https://agentmods.dev/badge/skills/taosdata/agent-skills/idmp-analysis.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 | $0.00038 | $0.02137 |
| Opus 5 | $0.00019 | $0.01069 |
| Sonnet 5 | $0.00008 | $0.00427 |
| Haiku 4.5 | $0.00004 | $0.00214 |
Grade A, and why
idmp-analysis 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 7d 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.
analysis
Read ../idmp-shared/SKILL.md first.
Before any write: Follow the 🛑 Destructive op confirmation protocol. Read-only commands stay read-only here, but delete / write / patch flows still require the shared yes-gate.
Recommended shortcuts
| Shortcut | Purpose |
|---|---|
+list |
Read analyses under one element. |
+search |
Search analyses globally, including an empty-keyword starting point. |
Recommended references
analysis read flows../idmp-workflow-analysis-create/SKILL.md../idmp-workflow-alert-create/SKILL.md
Missing context to resolve first
| Context | Why it must be resolved before create or resume |
|---|---|
| Final owner and mode | You need the exact elementId or elementTemplateId before you can choose the right command family or reserve a name. |
| Business root | Element-mode analysis creates still need rootElementId from the business root, even when the real owner moves to a data-bearing leaf. Prove that root with element elements path plus element fullpath get before you send the create payload. |
| Candidate analysis name | analysis.analyses.new-name and analysis-template.analyses.new-name require a candidate name. |
| Trigger scope | You need to know applyOnSelf, child-template scope, and which trigger type is valid after that choice. |
| Output plan | Decide whether to reuse or create output attributes, which valueType they need, and whether they land on self or child scope. |
| Runtime target | Decide whether Ready is acceptable or whether the final workflow must end in Running and therefore needs resume. |
Constrained live behaviors
- Prefer
POST /api/v1/ai/analysis/createfor natural-language analysis or alert intents, then persist the returned draft through the normal create path. Use the structured DTO workflow as the fallback when the draft is unsuitable or persistence fails. analysis.analyses.new-nameandanalysis-template.analyses.new-namerequire a candidatenameand--ack-risk; do not call them with only the owner scope.- In element mode,
rootElementIdcomes from the business root rather than the current leaf element. - Shared environments can force analysis creation onto a data-bearing leaf when
trigger-types listis empty on the current owner. - Child scope does not inherit self-scope triggers. When
applyOnSelf=false, the backend can legitimately expose onlySessionandInterval, so do not assumeDataInputorEventwill stay available. - Minimal create payloads need
rootElementId,startAfterCreated, a validtrigger, and realoutput.attributes[].attrIdvalues. For current liveELE_SUBETflows, child-scope analyses can use owner-element output attributes whileoutput.elementTemplate.idcontinues to point at the child template. - Analysis create is not complete until
get,list, and, when needed,resumeprove the backend kept the object in the expected runtime state. - Current live backends can return success for analysis delete while the generated output attributes remain referenced. Once create, reread, and
resumeprove the analysis itself worked, classify leaked output-attribute cleanup as a backend boundary instead of a wrong create payload. - If the workflow must emit events or notifications, switch to
../idmp-workflow-alert-create/SKILL.mdinstead of treating it as a generic read or create flow.
What ships with it
1 file 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.
- 7d ago First seen · 113 lines · 38 tokens per session scan A 4f236e1ad5bd
idmp-analysis is a skill published in the GitHub repository taosdata/agent-skills (3 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 2,137 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…