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 wangsiyi7/codex-reasoning-reactor --skill reasoning-budgetgit clone --depth 1 https://github.com/wangsiyi7/codex-reasoning-reactorWrote 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/wangsiyi7/codex-reasoning-reactor/reasoning-budget)<a href="https://agentmods.dev/skills/wangsiyi7/codex-reasoning-reactor/reasoning-budget"><img src="https://agentmods.dev/badge/skills/wangsiyi7/codex-reasoning-reactor/reasoning-budget/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/wangsiyi7/codex-reasoning-reactor/reasoning-budget"><img src="https://agentmods.dev/badge/skills/wangsiyi7/codex-reasoning-reactor/reasoning-budget.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 | $0.00039 | $0.00389 |
| Opus 5 | $0.00019 | $0.00195 |
| Sonnet 5 | $0.00008 | $0.00078 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
reasoning-budget 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 9d 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
Reasoning Budget
Use this skill when the user asks which Codex model or reasoning level to use, asks about speed or quota trade-offs, or wants the interactive reasoning-budget panel.
Workflow
- Summarize the task in one concise sentence without inventing scope.
- Infer
scopeconservatively:tiny: one narrow answer or edit.small: a focused change in a few files.medium: a feature, diagnosis, or multi-step analysis.large: broad migration, research, or cross-project work.
- Call
estimate_reasoning_budgetfor analysis orshow_reasoning_budgetwhen the user wants to compare, see, choose, or interact with the budget. - Explain that time and quota are local estimates, not OpenAI billing or a guarantee.
- Treat Ultra as multi-agent parallel work, not merely a stronger single-agent reasoning level. Prefer Max when a hard task is not meaningfully divisible.
- Do not claim the plugin changed Codex's native model picker. The separate local native adapter owns that unsupported host-UI bridge.
- Call
record_reasoning_outcomeonly when the user explicitly asks to record/calibrate an actual outcome, and passconsent: true. The ledger intentionally does not retain the task summary.
Model guidance
- Luna: clear, repeatable, high-volume tasks.
- Terra: everyday engineering and balanced tool use.
- Sol: ambiguous, complex, high-value work requiring judgment and polish.
When recommending, state the chosen model and level first, then give estimated time, relative quota, and the main trade-off in one compact paragraph.
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.
- 9d ago First seen · 31 lines · 39 tokens per session scan A f6baaf120b67
reasoning-budget is a skill published in the GitHub repository wangsiyi7/codex-reasoning-reactor (0 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 389 once invoked, about $0.0002 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
holon-runtime-ops
Operate and diagnose Holon runtimes with metadata-only patrol reports, incremental error analysis, and sanitized bug escalation.
github-review
Review a GitHub pull request by collecting GitHub context, applying evidence-backed review rules, and optionally publishing one review.
ops
Operate servers and services with read-only-first diagnosis, explicit authorization, auditable inventory, operation records, rollback, and verification.
github-pr-fix
Fix a GitHub pull request by addressing feedback or CI failures, pushing changes, and publishing replies.
session-summary
You summarise ONE work-burst of a developer's coding-agent session. The goal is to capture what the developer actually worked on, and why it mattered, so that a PM, a teammate, or the developer themselves can immediately understand the purpose and the outcome at a glance — without reading the transcript.
reduce
Use when asked to simplify, clean up, tidy, or refactor code for clarity without changing what it does, or when the user says "simplify this", "clean this up", "make it readable", "reduce the complexity", or "tidy this". Behavior-preserving only; not a bug or security audit (use bug-hunt or security-sweep for those).