codexkit-mcp-onboarding

A guide for deciding whether a team should add MCP servers, which are connections that let an AI assistant use external tools or data.

In plain words
What is it for?
Planning MCP adoption for documentation lookup, issue tracking, repository information, or restricted observability data.
Why use it?
It helps teams choose only integrations that support real engineering tasks while controlling secrets, access, monitoring, and removal.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/hoavdc/codexkit/codexkit-mcp-onboarding
Any agent
npx skills add hoavdc/CodexKit --skill codexkit-mcp-onboarding
Clone the repo
git clone --depth 1 https://github.com/hoavdc/CodexKit

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 445 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00028 $0.00445
Opus 5 $0.00014 $0.00222
Sonnet 5 $0.00006 $0.00089
Haiku 4.5 $0.00003 $0.00044

Measured 2d ago against content hash 1738e71bab0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codexkit-mcp-onboarding 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 2d 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.

skills/codexkit-mcp-onboarding/SKILL.md · 58 lines

What it actually says

MCP Onboarding

Use this skill when deciding whether a repo or team should add MCP servers and how to roll them out safely.

Workflow

  1. Start from real engineering tasks, not tool hype.
  2. Map each task to the minimum useful MCP capability.
  3. Prefer read-only or low-risk integrations first.
  4. Define who owns secrets, scopes, and monitoring.
  5. Document why each server exists and when to remove it.

Strong candidates

  • docs and API lookup
  • issue tracker triage
  • repository metadata and pull request context
  • observability lookups with strict access control

Avoid

  • installing every available MCP server
  • shipping write access without auditability
  • embedding team-specific secrets in public examples

Quality Criteria

  • Steps are executable in sequence without external context
  • Decision points have clear if/then branching
  • Rollback or abort procedures are documented for risky steps
  • Expected duration or time-per-step is estimated

Verification (4C)

Check Question
Correctness Do the steps execute correctly in the order specified?
Completeness Are decision points, error handling, and escalation paths all documented?
Context-fit Could someone with the right access but no prior context complete this runbook?
Consequence If Step N fails and the operator skips to Step N+1, what breaks?

Edge Cases

  • Steps require access the operator doesn't have — Document exact access requirements upfront. Include escalation contact for emergency access.
  • Environment differs from documented state — Add a pre-flight check as Step 0 to verify prerequisites before starting.
  • Runbook is triggered during off-hours — Document who to contact and which steps can be safely deferred to business hours.

Changelog

  • v1.0.0 — Initial release
Files

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.

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. 2d ago First seen · 58 lines · 28 tokens per session scan A 1738e71bab0a

Subscribe to this mod's changes

codexkit-mcp-onboarding is a skill published in the GitHub repository hoavdc/CodexKit (21 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 445 once invoked, about $0.0001 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.