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 yksanjo/codex-conductor --skill skillgit clone --depth 1 https://github.com/yksanjo/codex-conductorWrote 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/yksanjo/codex-conductor/skill)<a href="https://agentmods.dev/skills/yksanjo/codex-conductor/skill"><img src="https://agentmods.dev/badge/skills/yksanjo/codex-conductor/skill/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/yksanjo/codex-conductor/skill"><img src="https://agentmods.dev/badge/skills/yksanjo/codex-conductor/skill.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 | $0.00054 | $0.00535 |
| Opus 5.5 | $0.00022 | $0.00214 |
| Sonnet 5.5 | $0.00011 | $0.00107 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
codex-conductor 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 2mo 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.
What it actually says
Codex Conductor
You are using Codex Conductor as a read-only session supervisor. It reads local Codex transcripts and reports what other sessions appear to be doing. Do not interrupt or type into other sessions unless the user explicitly asks for control.
Step 1 - Gather Sessions
Run the scanner:
node ~/codex-conductor/scan.js --json --minutes 30
It scans ~/.codex/sessions/**/*.jsonl, uses ~/.codex/session_index.jsonl for
thread names when available, groups by session id, and returns structured JSON.
Widen the window with --minutes 60, or pass --all when the user wants older
local history.
Step 2 - Render The Table
For each session, use:
label/project- where it is working.title,task, andintent- what the session appears to be about.recentandlastAction- what happened recently.lastActiveRel- how long since real activity.status- active, open, recent, or idle.
Output format:
N Codex sessions
* <label> · <status> · <lastActiveRel>
doing now : <one-line inference from lastAction/recent>
done : <best-effort summary from recent records>
what's left: <best-effort next step; mark uncertain guesses with ?>
Rules
- "What's left" is inference, not fact. The transcript shows activity, not a confirmed todo list.
- Keep it scannable. The user is triaging sessions, not reading a report.
- If
countis 0, say no recent Codex sessions were found and suggest--minutes 60or--all. - This skill is read-only. For control, point the user at
codex-conductor run <label>,codex-conductor say <label> <text>, andcodex-conductor adopt <id>, or use the MCP tools if available. auto_continueruns under the irreversibility gate and refuses unattended deploy, send, delete, or spend approvals.
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.
- 2mo ago First seen · 57 lines · 54 tokens per session scan A 084ac55710b0
codex-conductor is a skill published in the GitHub repository yksanjo/codex-conductor (1 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 535 once invoked, about $0.0002 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.
Other skills, from other repositories
subscription-setup
A setup workflow for creating recurring medical-learning subscriptions after a doctor’s profile has been registered.
dws
A command-line guide for DingTalk, a workplace platform with chat, documents, calendars, approvals, tasks, and other business tools.
tmeet-skill
A command-line tool for Tencent Meeting, a video-conferencing service. It covers sign-in, meetings, recordings, transcripts, reports, invitations, and controls during a meeting.
anarlog
Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history, or import a local recording. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.
lody-automations
Register a background condition that resumes this Session when ready, inspect or cancel waits, and configure quota recovery, idle compaction or archive after merge.
calendly
Manage Calendly scheduling via the v2 API. List event types, view scheduled events, check invitee details, manage availability schedules, cancel/reschedule events, create one-off links, and configure webhooks. Use when the user asks about their calendar, upcoming meetings, scheduling links, or availability.