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 jgassens/codex-terminal-pro --skill consultgit clone --depth 1 https://github.com/jgassens/codex-terminal-proWrote 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/jgassens/codex-terminal-pro/consult)<a href="https://agentmods.dev/skills/jgassens/codex-terminal-pro/consult"><img src="https://agentmods.dev/badge/skills/jgassens/codex-terminal-pro/consult.svg" alt="Measured on agentmods" 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 | $0.00114 | $0.00940 |
| Opus 5 | $0.00057 | $0.00470 |
| Sonnet 5 | $0.00023 | $0.00188 |
| Haiku 4.5 | $0.00011 | $0.00094 |
Grade A, and why
consult 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consulting a second model
This add-on may have consultants configured: other coding CLIs signed in with the user's own subscriptions. They are advisors only. You remain the agent doing the work, and you own the final answer.
Checking what is available
consult --list
Consultants are optional and are set up by the user in the add-on's Settings panel. If none is signed in, say so plainly and carry on yourself rather than treating it as a blocker.
Asking
For a real second opinion, ask both consultants at once:
consult --agents kimi,claude "Question here, with enough context."
They run in parallel and are independent opinions, not a primary and a backup. Answers stream back fastest first, each in a labelled block. Kimi usually lands first; if her answer already settles the question, act on it and move on - you need not wait for Claude. If it does not, wait for Claude's slower, deeper answer, which the same command prints when it arrives.
Ask a single consultant only when you specifically want just one:
consult --agent kimi "Question here."
consult "Question here." # the default consultant from Settings
The question is the whole prompt, so write it as you would to a competent colleague who has not seen the conversation: state the goal, what you already tried, and what specifically you want judged. Name the files worth reading; the consultant opens its own filtered snapshot copies.
A consult that reads files at high effort can take several minutes - that is
the intelligence you asked for working, not a hang. Each consultant answers
under its own timeout (default 600s); one that overruns is reported as "no
answer" for that consultant while the others still stand. Raise the limit with
--timeout SECONDS, up to 1800. Do not launch the same consultant twice over
one question; asking different consultants together is what --agents is for.
What the consultant can see
It runs as a dedicated unprivileged user whose working directory is a
bounded, root-owned text snapshot of /config - never the live /config or
/data trees - with .storage, secrets.yaml, credential/key files,
databases, logs, backups, symlinks, binary files, and oversized files left
out. Where the kernel provides Landlock it is added on top to block reads
outside the snapshot by absolute path. Common
inline token and secret assignments are redacted in the snapshot. It can write
only to its disposable credential home, which is deleted after the answer.
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.
- 2d ago Changed · +16 lines · +8 tokens per session 74fc98b846e6
- 7d ago First seen · 72 lines · 106 tokens per session scan A 780c34ce52ee
consult is a skill published in the GitHub repository jgassens/codex-terminal-pro (1 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 940 once invoked, about $0.0006 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.
Other skills, from other repositories
codex-memory-trim
A procedure for managing Codex's global memory, including removing duplicates, shortening verbose entries, and adding user-defined rules or preferences.
CodexClaw
Install and operate a Telegram bot that exposes Codex, MCP, GitHub subagents, repo switching, and minimal frontend dev-server control.
recap
Summarize the last N agent sessions for the current project, grouped by date, with highlight observations per session. Use when the user asks "recap", "what have we been doing", "today", "this week", or wants a rollup of recent work.
ctxwise
Audit and optimize OpenAI Codex context locally, compile model and subagent profiles, detect capability drift, create redacted lockfiles, inspect model-visible prompt structure, and render honest token, credit, quota, or API-cost receipts. Use when the user explicitly invokes CtxWise or asks to run its installed CLI…
hermes-codex-operator
Act as a technical partner for planning, dispatching, following, verifying, and explaining local Codex engineering work through the hermes-codex CLI. Use for implementation tasks where Codex should do the coding; do not use as a general orchestrator or for unrelated shell work.
eco-max
Maximum-savings variant of eco - the same frugality rules with a tighter reply budget, for routine chores (rename, small fix, quick lookup, boilerplate). Prefer plain eco for hard or high-stakes work. Works in any language.