oiap-platform-matrix-refresh

oiap-platform-matrix-refresh is a skill for Claude Code from fboldo/oiap. It costs 98 tokens per session (1,004 once invoked), scanned A, original, MIT.

A documentation-audit workflow for OIAP, a system that connects coding-agent platforms through adapters. It refreshes the platform support matrix using current platform documentation.

In plain words
What is it for?
Use it to review support for features such as hooks, MCP, skills, commands, rules, custom agents, runtime bridges, and package formats, then produce updated documentation and an adapter review report.
Why use it?
It helps reveal outdated platform support information and mismatches between documented features and implemented adapters.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions Codex.

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/fboldo/oiap/oiap-platform-matrix-refresh
Any agent
npx skills add fboldo/oiap --skill oiap-platform-matrix-refresh
Clone the repo
git clone --depth 1 https://github.com/fboldo/oiap

Made for: Claude Code.

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 oiap-platform-matrix-refresh

README.md
[![agentmods](https://agentmods.dev/badge/skills/fboldo/oiap/oiap-platform-matrix-refresh.svg)](https://agentmods.dev/skills/fboldo/oiap/oiap-platform-matrix-refresh)
Your own site
<a href="https://agentmods.dev/skills/fboldo/oiap/oiap-platform-matrix-refresh"><img src="https://agentmods.dev/badge/skills/fboldo/oiap/oiap-platform-matrix-refresh.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,004 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 5.1 $0.00098 $0.01004
Opus 5 $0.00049 $0.00502
Sonnet 5 $0.00020 $0.00201
Haiku 4.5 $0.00010 $0.00100

Measured 5d ago against content hash df52232c65b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

oiap-platform-matrix-refresh 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 5d 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.

.agents/skills/oiap-platform-matrix-refresh/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OIAP Platform Matrix Refresh

Use this skill to refresh OIAP's platform support matrix from current platform documentation and compare the results against implemented OIAP adapters.

The workflow updates documentation and produces an adapter review report. It does not install host tools, mutate user agent configuration, or implement adapter code unless the user explicitly asks for that follow-up.

Inputs

The user may name one platform, several platforms, or all. If no scope is given, refresh the targets that are most likely to have changed or that have ? marks in MATRIX.md.

Read First

Read these files before researching:

  • ARCHITECTURE.md
  • MATRIX.md
  • package.json

Then inspect adapter code if it exists:

rg --files packages .agents | rg 'exporter|adapter|profile|target|platform'

If no adapter packages exist, treat adapter checks as planned-package checks and say that no implementation comparison was possible yet.

Research Procedure

  1. Resolve the platform scope.
  2. Start from the Documentation Sources table in MATRIX.md.
  3. Use the queries in platform-source-queries.md to find feature-specific docs and replacement official sources for rows marked needs verification.
  4. Prefer official docs, canonical vendor repositories, and release notes.
  5. Use community posts only as leads. Do not cite them as source of truth unless no official source exists, and mark that evidence as unverified.
  6. For each platform, extract evidence for package, rules, skills, commands, hooks, agents/delegation, MCP/tools, runtime adapter needs, permissions, and policy controls.
  7. Record dates and URLs in your working notes so the final summary can explain what changed.

When official docs cannot be found or are ambiguous, keep the matrix mark as ? and add a short note instead of guessing.

Matrix Update Rules

Use the existing legend in MATRIX.md:

  • Y: native or first-class target surface expected.
  • P: partial support, profile-dependent support, or likely support needing verification.
  • F: OIAP fallback support.
  • R: runtime bridge required.
  • N: not expected.
  • ?: needs verification.

Read the full file on GitHub · 125 lines

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. 5d ago First seen · 125 lines · 98 tokens per session scan A df52232c65b3

Subscribe to this mod's changes

oiap-platform-matrix-refresh is a skill published in the GitHub repository fboldo/oiap (5 stars, last pushed 3mo ago), licensed MIT. It adds 98 tokens to every session and 1,004 once invoked, about $0.0005 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.

Related

Other skills, from other repositories