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 Abhillashjadhav/AI-PM-essential-skills --skill mcp-migration-auditorgit clone --depth 1 https://github.com/Abhillashjadhav/AI-PM-essential-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/abhillashjadhav/ai-pm-essential-skills/mcp-migration-auditor)<a href="https://agentmods.dev/skills/abhillashjadhav/ai-pm-essential-skills/mcp-migration-auditor"><img src="https://agentmods.dev/badge/skills/abhillashjadhav/ai-pm-essential-skills/mcp-migration-auditor/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.
<a href="https://agentmods.dev/skills/abhillashjadhav/ai-pm-essential-skills/mcp-migration-auditor"><img src="https://agentmods.dev/badge/skills/abhillashjadhav/ai-pm-essential-skills/mcp-migration-auditor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00220 | $0.01524 |
| Opus 5.5 | $0.00088 | $0.00610 |
| Sonnet 5.5 | $0.00044 | $0.00305 |
| Haiku 4.5 | $0.00022 | $0.00152 |
Grade A, and why
mcp-migration-auditor 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 1mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Migration Auditor
Review MCP configs for the selected 2026-07-28 migration risks below. For each finding, name the target version, observed evidence, source and remaining unknowns. A scoped clearance is not a full compatibility certificate.
Source status: rules rechecked on 2026-09-28 against the versioned
specification; see references/spec-changes.md. July 28 is a past revision date.
Record the deployed protocol/client/SDK versions before applying a migration
verdict. These selected checks are not full protocol conformance.
Step 1 — Locate configs
Search the project for MCP configs, in this order: .mcp.json, mcp.json, claude_desktop_config.json, mcpServers blocks inside .claude/settings.json / .claude/settings.local.json / other settings files. If none found, ask the user to paste one — never audit an imagined config.
Step 2 — Classify transport per server
command-based entries → stdio/local. HTTP session changes alone do not establish a transport failure; inspect shared protocol/capability rules before any broader verdict.url-based entries (HTTP / Streamable HTTP / SSE) → remote. These get the full rule pass.
Step 3 — Apply the verified rules
| Rule | Evidence to look for | Verdict | Source |
|---|---|---|---|
| R1 — Protocol session dependency | Mcp-Session-Id in headers, session-affinity/sticky-session settings, session-store references for an MCP endpoint |
BREAKS — header and protocol-level session removed | SEP-2567 |
| R2 — Handshake pinning | custom client/server code pinned to initialize/initialized; version negotiation done once at connect |
BREAKS — handshake removed; protocol version and capabilities travel in _meta per request; client identity is recommended; server/discover replaces capability exchange |
SEP-2575 |
| R3 — Deprecated capabilities | server uses roots, sampling, or logging (config flags, docs, or user confirmation) | DEGRADED — deprecated feature; inspect specific method removals and the current lifecycle registry | SEP-2577, SEP-2596 |
| R4 — Experimental Tasks | server or client shipped against the 2025-11-25 experimental Tasks API | BREAKS — Tasks moved to an official extension with a new lifecycle; tasks/list removed |
SEP-2663 |
| R5 — OAuth patterns | remote server using OAuth: no validation of a present iss, credentials assumed portable across authorization servers, missing application_type in dynamic client registration |
DEGRADED — action required for compliance: validate iss (RFC 9207), re-register credentials (issuer-bound), declare application_type |
SEP-2468, SEP-2352, SEP-837 |
| R6 — Stdio transport scope | command-based; other applicable checks explicitly resolved |
SAFE for checked scope — list unconfirmed rules separately | official announcement, "Unaffected Deployments" |
What ships with it
3 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.
- 1mo ago Changed · +6 lines · -8 tokens per session bf9d14d307c5
- 2mo ago First seen · 63 lines · 228 tokens per session scan A 0368ed6f323d
mcp-migration-auditor is a skill published in the GitHub repository Abhillashjadhav/AI-PM-essential-skills (9 stars, last pushed 17d ago), licensed MIT. It adds 220 tokens to every session and 1,524 once invoked, about $0.0009 per session on Opus 5.5. 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.
mcp-migration-auditor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-migration-auditorAbhillashjadhav/AI-PM-essential-skills | Skill | 9 | 17d ago | MIT | A | 220 | Claude Code |
| research-reportShenSeanChen/waku-agent | Skill | 2.2k | 17d ago | MIT | A | 0 | Claude Code, Codex |
| building-agentsericrisco/rsc-harness | Skill | 573 | yesterday | MIT | A | 85 | Claude Code, Codex |
| debloatLilMGenius/paperthin | Skill | 1.4k | yesterday | MIT | A | 178 | Claude Code, Codex |
| re0-gitLilMGenius/paperthin | Skill | 1.4k | yesterday | MIT | A | 61 | Claude Code, Codex |
| re0-importLilMGenius/paperthin | Skill | 1.4k | yesterday | MIT | A | 84 | Claude Code, Codex |
| re0-workflowLilMGenius/paperthin | Skill | 1.4k | yesterday | MIT | A | 86 | Claude Code, Codex |