poppify-schema-introspect

poppify-schema-introspect is a skill for Claude Code from Poppify/poppify-claude-plugin. It costs 94 tokens per session (1,252 once invoked), scanned A, original, MIT.

Instructions for checking the live parameter schemas of Poppify MCP tools. MCP tool schemas define which fields a client is allowed to send, so undeclared fields may be discarded before the server receives them.

In plain words
What is it for?
Use them to inspect accepted parameters, investigate ignored settings, and confirm current tool names and request shapes before recommending fields.
Why use it?
They help explain why a parameter was ignored and distinguish a schema mismatch from a problem in the tool handler.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the poppify plugin — 7 skills, 3 commands, 1 MCP server shipped together

Good fit Use them to inspect accepted parameters, investigate ignored settings, and confirm current tool names and request shapes before recommending fields.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/poppify/poppify-claude-plugin/poppify-schema-introspect
Install

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.

Any agent
npx skills add Poppify/poppify-claude-plugin --skill poppify-schema-introspect
Clone the repo
git clone --depth 1 https://github.com/Poppify/poppify-claude-plugin

Made for: Claude Code.

Or install poppify, the plugin that ships this one along with the rest of its 7 skills, 3 commands, 1 MCP server.

Wrote 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.

agentmods badge for poppify-schema-introspect

README.md
[![agentmods](https://agentmods.dev/badge/skills/poppify/poppify-claude-plugin/poppify-schema-introspect/github.svg)](https://agentmods.dev/skills/poppify/poppify-claude-plugin/poppify-schema-introspect)
Your own site
<a href="https://agentmods.dev/skills/poppify/poppify-claude-plugin/poppify-schema-introspect"><img src="https://agentmods.dev/badge/skills/poppify/poppify-claude-plugin/poppify-schema-introspect/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.

agentmods 80×15 button for poppify-schema-introspect

Your own site · 80×15
<a href="https://agentmods.dev/skills/poppify/poppify-claude-plugin/poppify-schema-introspect"><img src="https://agentmods.dev/badge/skills/poppify/poppify-claude-plugin/poppify-schema-introspect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,252 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.01252
Opus 5 $0.00047 $0.00626
Sonnet 5 $0.00019 $0.00250
Haiku 4.5 $0.00009 $0.00125

Measured 9d ago against content hash 3b1e1d6a18a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

poppify-schema-introspect scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s https://poppify.ai/api/mcp \
skills/poppify-schema-introspect/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inspecting the deployed Poppify MCP schemas

MCP clients strip undeclared fields before forwarding to the server. If a parameter you pass to a tool seems to have been ignored, the most likely cause is schema/code drift — the server's handler accepts the field, but the MCP tool registration's Zod schema doesn't declare it, so the field was dropped at the protocol boundary.

This skill teaches Claude how to verify the deployed schema directly.

Jul 2026 consolidation note: the deployed surface was consolidated from 37 tools to 28 — old names were merged, not dropped, and two NEW tools were added: publish_post (post now / schedule to connected channels, linked accounts only) and portfolio (list / switch the active portfolio). customize / set_audio / set_voiceoverapply_session_patch; update_visualupdate_slides({action:"set_image"}) (replace) + apply_session_patch({visualEdits:[...]}) (insert/splice); preview_live_promptanimate_slide({dryRun:true}); generate_framesadd_slide_image (reference params, consistent-frames mode); list_recipes / get_recipe_optionsrecipes; get_balance / get_topup_url / linkwallet; suggest_image_prompt / suggest_music_promptsuggest_prompt({kind}); get_priceget_result (pre-confirm price breakdown). If a schema-vs-docs diff shows one of the old names missing from the live catalog, that's the consolidation — not drift.

Where to look

The MCP server publishes its tool catalog via the standard MCP tools/list request. Claude Code already calls this on connect — the tool definitions are available in the client's MCP state.

To inspect what was returned:

  1. List the tools Claude Code currently sees:

    /mcp poppify
    

    That shows the names, but not the param shapes.

  2. For the param shapes, ask the deployed server directly via JSON-RPC tools/list at the canonical MCP endpoint (https://poppify.ai/api/mcp, POST — the Poppify server is stateless, no initialize handshake needed):

    curl -s https://poppify.ai/api/mcp \
      -H 'Content-Type: application/json' -H 'Accept: application/json, text/event-stream' \
      -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' \
      | sed -n 's/^data: //p' | jq '.result.tools[] | select(.name=="apply_session_patch") | .inputSchema'
    

Read the full file on GitHub · 65 lines

Changes

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.

  1. 9d ago First seen · 65 lines · 0 tokens per session scan A 3b1e1d6a18a6

Subscribe to this mod's changes

poppify-schema-introspect is a skill published in the GitHub repository Poppify/poppify-claude-plugin (0 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,252 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

release-it

Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or…

wondelai/skills · 131 tokens

tidewave-integration

Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.

oliver-kriska/claude-elixir-phoenix · 38 tokens

de-vibe

Audit and fix the tells that software was vibe-coded / AI-generated, then give it a small distinctive identity, so it ships looking handcrafted and professional. Use whenever the user says "de-vibe", "does this look AI-generated / vibe coded?", "make this look shippable / handcrafted / professional", "remove the AI…

ucsandman/marketing-studio · 128 tokens

debug

Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.

sd0xdev/sd0x-harness · 67 tokens

git-investigate

Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report.

sd0xdev/sd0x-harness · 53 tokens

analyze

Deep-dive codebase analysis that explains how things actually work — business rules, architecture patterns, auth flows, data models, integrations, and performance hotspots. Use whenever the user asks "how does X work", "map the Y flow", "what are the business rules for Z", "trace the auth path", "explore the codebase…

rsmdt/the-startup · 118 tokens