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 j-token/codex-mcp --skill gpt-5-5-promptinggit clone --depth 1 https://github.com/j-token/codex-mcpWrote 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/j-token/codex-mcp/gpt-5-5-prompting)<a href="https://agentmods.dev/skills/j-token/codex-mcp/gpt-5-5-prompting"><img src="https://agentmods.dev/badge/skills/j-token/codex-mcp/gpt-5-5-prompting/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/j-token/codex-mcp/gpt-5-5-prompting"><img src="https://agentmods.dev/badge/skills/j-token/codex-mcp/gpt-5-5-prompting.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 | $0.00047 | $0.00609 |
| Opus 5 | $0.00023 | $0.00304 |
| Sonnet 5 | $0.00009 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
gpt-5-5-prompting 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPT-5.5 Prompting
Prompt Codex like an operator handing off a single-turn brief, not a collaborator you chat with. Codex performs best single-turn: give it the destination and the waypoints (goal + success criteria + constraints) and it will navigate the rest on its own.
Core rules
- One clear task per run. Split unrelated asks into separate runs.
- Tell Codex what "done" looks like. Do not assume it infers the desired end state.
- Put
must/neverrules explicitly in the prompt. Codex keeps them across a long context and across compaction, so state them once, plainly. - Prefer a tighter contract over raising reasoning effort or writing long prose.
- Default to
model: gpt-5.5,reasoning_effort: medium. Raise effort only after a tighter prompt has failed.
Template
Task: <the problem in one sentence>
Success means:
- <acceptance condition>
- <acceptance condition>
- <item that must appear in the final output>
Constraints:
- <invariant must/never that holds only for THIS task>
Output: <exact shape, ordering, brevity>
Constraint hygiene
Constraints holds only invariants specific to this task. Do NOT put in:
- Rules the tool already guarantees. If you called the tool
read-only, do not also write "do not edit files." Pick the read-only mode instead of restating it. - Generic quality platitudes ("don't guess", "be accurate"). These apply to every
task and are not constraints. Encode them instead as verifiable items under
Success means— e.g. "every finding citesfile:line", "note each assumption".
Blocks to add by task type
- Review / adversarial review: grounding (cite
file:line, mark hypotheses as hypotheses), a structured findings contract, and a "dig one level deeper" nudge. - Debug / implementation: fix the root cause, not the symptom; add a verification step (build/test/repro); list what changed and why; stop and ask only if a high-risk detail is missing.
- Logic / math / formula verification: show the derivation, state assumptions explicitly, and give a runnable check or a concrete counterexample.
- Research / recommendation: cite sources for each claim.
- Write-capable runs: keep the change narrow; no unrelated refactors.
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 · 58 lines · 47 tokens per session scan A 7f3702b82052
gpt-5-5-prompting is a skill published in the GitHub repository j-token/codex-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 609 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
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…