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 agentmods add skills/majiayu000/spellbook/codexnpx skills add majiayu000/spellbook --skill codexgit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/majiayu000/spellbook/codex)<a href="https://agentmods.dev/skills/majiayu000/spellbook/codex"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/codex.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 | $0.00038 | $0.02001 |
| Opus 5 | $0.00019 | $0.01001 |
| Sonnet 5 | $0.00008 | $0.00400 |
| Haiku 4.5 | $0.00004 | $0.00200 |
Grade A, and why
codex 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 today.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Skill Guide
Operating Contract
- Run
codex --versionandcodex exec --helpfirst. Stop if Codex is unavailable, and only use flags shown by the installed CLI. - If the user did not specify a model or reasoning effort, use the installed default. Do not hardcode a model list; model names and supported reasoning levels change over time.
- Select the smallest sandbox needed:
--sandbox read-onlyfor inspection and--sandbox workspace-writefor requested local edits. Network access, extra writable roots, and broader modes are separate grants. - Assemble the command from supported options such as:
-m, --model <MODEL>--config model_reasoning_effort="<LEVEL>"--sandbox <read-only|workspace-write|danger-full-access>-C, --cd <DIR>--add-dir <DIR>--json--ephemeral--skip-git-repo-check--dangerously-bypass-approvals-and-sandbox
- Do not use
--skip-git-repo-checkby default. Use it only when the user explicitly asks to run outside a Git repository or has approved that boundary bypass for this command. - Do not use deprecated compatibility shortcuts such as
--full-auto; use the explicit sandbox shown by current help. - Preserve stderr. Keep it out of the parent context by writing it to a bounded artifact and reading only the exit status, short tail, or targeted diagnostics. Never redirect it to
/dev/null. - For automation, batch work, cost investigation, or any run that needs measured usage, add
--jsonand save stdout as JSONL. Read the final usage event and report input, cached input, output, and reasoning tokens when present. - Enforce a hard wall-clock timeout with the supervising runtime. Stop on non-zero exit or timeout; do not automatically retry an expensive run.
- When continuing a genuinely conversational task, use
codex exec resume --lastvia stdin. Do not resume a session for homogeneous record batches; start a fresh bounded--ephemeralrun per tranche so accumulated history is not resent on every model call.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · +69 lines 9ed445e66c0a
- 5d ago First seen · 63 lines · 38 tokens per session scan A d8ec1a538ea3
codex is a skill published in the GitHub repository majiayu000/spellbook (265 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 2,001 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 2026-08-30.
Other skills, from other repositories
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
security
Enforce Elixir/Phoenix security — auth, OAuth, sessions, CSRF, XSS, SQL injection, input validation, secrets. Use when editing auth files, login flows, RBAC, or API keys.
michel-cli-demo-recorder
Produce proof-of-execution demos of the Packmind CLI (packmind-cli) as terminal-styled images (colors and formatting preserved exactly), for embedding in a GitHub PR. Renders a crisp master SVG and rasterizes it to a PNG — the PNG is what you embed, because GitHub does not render SVG in PR/issue bodies. Use this…
general-video
The fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand / sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a…
session-scan
Compute metrics for Claude Code sessions. Discovers via ccrider, filters trivial, computes friction/opportunity/fingerprint scores. Use for broad session triage.