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/takeoff69/codex-skills-kit/codex-promptnpx skills add TAKEOFF69/codex-skills-kit --skill codex-promptgit clone --depth 1 https://github.com/TAKEOFF69/codex-skills-kitWrote 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/takeoff69/codex-skills-kit/codex-prompt)<a href="https://agentmods.dev/skills/takeoff69/codex-skills-kit/codex-prompt"><img src="https://agentmods.dev/badge/skills/takeoff69/codex-skills-kit/codex-prompt.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 | $0.00077 | $0.05586 |
| Opus 5 | $0.00039 | $0.02793 |
| Sonnet 5 | $0.00015 | $0.01117 |
| Haiku 4.5 | $0.00008 | $0.00559 |
Grade A, and why
codex-prompt scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- UI work requires observable proof (browser/curl/screenshot) beyond build success How it starts
The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Prompt Generator
Generates copy-paste-ready Codex prompts that ship self-contained – Codex runs locally with full repo access and executes without clarification turns.
Foundations
These two principles outrank the category templates below. When a category rule and a foundation tension, follow the foundation.
Karpathy (higher authority). State assumptions; present interpretations when ambiguous; push back when a simpler path exists; stop and ask when confused. Ship the minimum code that solves the problem – every line traces back to the request. Transform tasks into verifiable goals: success criteria + stop condition, let Codex loop until verified.
Directional. Open every prompt with Goal + Success means + Stop when. Lead each instruction with a positive verb naming the correct action. Demote decorative ALWAYS/NEVER/MUST to plain prose; reserve them for true invariants (safety boundaries, hard limits, required output fields). Negation survives in four narrow cases: hard safety, near-identical-path disambiguation, acceptable-space too large to enumerate, narrower-than-any-positive-paraphrase (incident-derived rules tagged Past incident: qualify under case 4).
Task types
| Type | Use | Key trait |
|---|---|---|
| Fix | Known-root-cause bug | Broken code + corrected code |
| Build | Feature from design doc | Phased + schemas |
| Ops/Tuning | Runtime/deploy/infra/measurement | Live baseline + before/after metrics |
| Audit | Read-only analysis | PASS/FAIL tables + output format |
| PR-series | Multi-PR feature | Numbered PRs + deps |
| Refactor | Restructure w/o behavior change | Before/after + invariant |
Task mode (orthogonal to task type)
Every prompt picks one mode. The mode shapes what the prompt ships and how much room Codex has to think.
| Mode | When | Prompt ships |
|---|---|---|
| Directive | HOW is known (mechanical sweep, known-root-cause fix, target structure decided) | Exact steps, before/after code, target schema. Codex executes the spec. |
| Investigative | HOW is open (root-cause hunt, novel bug, ambiguous design space, finding all the ways a thing breaks) | Goal + success criteria + invariants + stop condition. Codex investigates, proposes, then acts. |
What ships with it
3 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.
- 5d ago First seen · 330 lines · 77 tokens per session scan A 9904fac1c6f5
codex-prompt is a skill published in the GitHub repository TAKEOFF69/codex-skills-kit (7 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 5,586 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
manage-codex-skills
Inventory, classify, route, catalog, relocate, or validate Codex skills and generate a skills menu. Use for skill-library organization or when Codex must find task-relevant skills. Classification, relocation, creation, revision, and promotion require user approval.
reflect-codex-workflows
Compare evidence from a current or completed project with installed skills and decide whether to reuse, revise, create, or not skill the lesson. Use for workflow reflection or proposed skill upgrades. Do not edit skills without explicit authorization.
bootstrap-codex-workspace
Inspect a Windows or macOS Codex environment and produce a read-only, approval-bound plan for the global AGENTS.md path, user skills root, and root for future projects. Use for workspace setup, bootstrap, or location planning. Do not write outside the repository until the user approves the exact plan ID.
organize-codex-projects
Choose a location and internal structure for a future Codex project, including focused projects and umbrella projects with durable subprojects. Use when creating or planning a new project. Do not move, rename, or normalize existing projects.
maintain-project-ai-records
Initialize and maintain lightweight AI work records in a writable project. Use on the first substantive writable task and after meaningful milestones. Do not create records for read-only inspection or trivial answers.
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.