iris-sync

A context-sync command that reads a saved Codex conversation log and summarizes the current work, progress, unresolved topics, and likely next direction.

In plain words
What is it for?
Use it when Claude Code needs a short summary of work previously done with Codex; if the log is missing, it reports that.
Why use it?
It removes the need to manually explain what happened in another coding-agent session.

Skill for Claude CodeCodex

Part of the iris plugin — 4 skills, 3 hooks shipped together

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/gsaranti/pantheon/iris-sync
Any agent
npx skills add gsaranti/pantheon --skill iris-sync
Clone the repo
git clone --depth 1 https://github.com/gsaranti/pantheon

Made for: Claude Code, Codex.

Or install iris, the plugin that ships this one along with the rest of its 4 skills, 3 hooks.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 353 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 $0.00057 $0.00353
Opus 5 $0.00028 $0.00177
Sonnet 5 $0.00011 $0.00071
Haiku 4.5 $0.00006 $0.00035

Measured 2d ago against content hash 3d3b15309652, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

iris-sync 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.

plugins/iris/.claude-code/skills/iris-sync/SKILL.md · 29 lines

What it actually says

Iris Sync

You are reading a record of a conversation between a user and Codex (a different AI coding assistant). Your job is to help the user's main Claude Code session understand what's been happening on the Codex side.

Codex chat log

!cat "${CLAUDE_PROJECT_DIR}/iris-codex-chat.md" 2>/dev/null || echo "[iris-codex-chat.md not found — Codex hasn't written any chat history to this project yet, or the Iris plugin isn't installed on the Codex side.]"

Your task

Read the chat log above and produce a brief synthesis covering:

  1. What they're working on. The current task, feature, or problem in one sentence.
  2. Recent progress. What has Codex done or attempted in the last few turns.
  3. Open threads. Anything unresolved, blocked, or explicitly deferred.
  4. The user's apparent intent. Where the user seems to be heading next, if it's clear from the conversation.

Keep the entire summary to 2–4 sentences. Do not quote the log verbatim. Do not speculate beyond what the log shows. If the log is empty or missing, say so plainly and stop.

Return the summary directly. The main Claude Code session will present it to the user.

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 · 29 lines · 57 tokens per session scan A 3d3b15309652

Subscribe to this mod's changes

iris-sync is a skill published in the GitHub repository gsaranti/pantheon (3 stars, last pushed 10d ago), licensed MIT. It adds 57 tokens to every session and 353 once invoked, about $0.0003 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.