Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add haenara-shin/codex-hud/plugin install codex-hudWrote 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/commands/haenara-shin/codex-hud/configure)<a href="https://agentmods.dev/commands/haenara-shin/codex-hud/configure"><img src="https://agentmods.dev/badge/commands/haenara-shin/codex-hud/configure.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 | $0.00014 | $0.02614 |
| Opus 5 | $0.00007 | $0.01307 |
| Sonnet 5 | $0.00003 | $0.00523 |
| Haiku 4.5 | $0.00001 | $0.00261 |
Grade A, and why
configure scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure Codex HUD
FIRST: Load current display configuration:
node "${CLAUDE_PLUGIN_ROOT}/dist/index.js" configure --get --json
Parse the JSON to determine current values. If _configured is true, use Flow B (existing user). Otherwise use Flow A (new user).
Defaults:
layout: "expanded",showPlan: true,showFooter: true,showUsage: true,showWeekly: true,showModel: true,showContext: true,resetStyle: "both",barWidth: 10,fallbackToWeek: true,language: "en"
Always On (not configurable)
- Codex header badge (
── Codex ──) - The data source (local Codex session logs at
~/.codex/sessions/) - Rate limit windows themselves (5h Usage, 7d Weekly)
- The red
⚠ LIMITalert when Codex reports a reached rate limit (it only appears while a limit is actually hit)
Advanced fields like colors are not yet exposed via this flow.
Live previews (use these in the option preview fields)
AskUserQuestion options support a preview field that renders next to the choices. Use it so the user SEES the effect before picking. Generate previews from the real renderer (never hand-write them — they must match the code):
node "${CLAUDE_PLUGIN_ROOT}/dist/index.js" preview --set <key>=<value> [--set <key>=<value> ...]
- It renders representative sample data as plain text (no color codes), with the overrides applied on top of the user's current saved config — so toggles the user already has set are reflected.
- For the Layout question (single-select, so previews ARE supported): run it once per layout (
--set layout=expanded,=horizontal,=inline,=compact) and put each result in that option'spreview. previewis NOT supported on multiSelect questions, so the on/off toggle questions have no per-option preview — instead show a combined preview in the final confirmation step.- Pass every override you're previewing together (e.g. when previewing layouts for an existing user who also turned off the plan badge, include
--set showPlan=false) so the preview matches what saving would actually produce.
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.
- 8d ago First seen · 240 lines · 14 tokens per session scan A fb4cc8b7fb58
configure is a command published in the GitHub repository haenara-shin/codex-hud (8 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 2,614 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.