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 dayfinggg/openai-codex-agent-skills --skill researchgit clone --depth 1 https://github.com/dayfinggg/openai-codex-agent-skillsWrote 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/dayfinggg/openai-codex-agent-skills/research)<a href="https://agentmods.dev/skills/dayfinggg/openai-codex-agent-skills/research"><img src="https://agentmods.dev/badge/skills/dayfinggg/openai-codex-agent-skills/research/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/dayfinggg/openai-codex-agent-skills/research"><img src="https://agentmods.dev/badge/skills/dayfinggg/openai-codex-agent-skills/research.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 | $0.00023 | $0.00253 |
| Opus 5.5 | $0.00009 | $0.00101 |
| Sonnet 5.5 | $0.00005 | $0.00051 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
research 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.
What it actually says
Read local host integration before applying this workflow.
Investigate the engineering question directly using primary sources.
- Recover the exact question, installed dependency versions, relevant integration, and constraints from the current conversation and repository.
- Read the relevant official documentation, specification, source code, or first-party API. A search snippet or page title does not establish the governing behavior.
- Match sources to the installed or explicitly selected version. Trace disputed or consequential claims back to their owner and reconcile material disagreements.
- Compare documented behavior with the actual integration and identify which finding changes the implementation decision. Do not expand into unrelated recommendations.
- Preserve the distinction between verified facts, inference, and unavailable evidence. Continue independent research while a genuinely necessary clarification is pending.
- Return concise, sourced findings in chat. Create a Markdown research file only when the user explicitly requests that deliverable. Use a background or separate agent only when explicitly authorized.
Finish when the question is answered to the precision required for the user's task. More sources are useful only when they resolve a material uncertainty.
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 First seen · 18 lines · 23 tokens per session scan A 5eb8fc8b9a79
research is a skill published in the GitHub repository dayfinggg/openai-codex-agent-skills (8 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 253 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-30.
Other skills, from other repositories
merge-pr
Merge a pull request with status checks, squash merge, and branch cleanup. Handles worktree contexts.
codex-autoresearch
Run repeated, measured Git experiments toward a numeric target; keep improvements and revert failures. Use for autonomous optimization or managing an autoresearch run, not one-shot edits.
bootstrap-prd
Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
code-that-fits-in-your-head
Software-engineering heuristics based on Mark Seemann's Code That Fits in Your Head (2021), updated for agent-driven development. Use when writing or reviewing code, refactoring accidental complexity or a Big Ball of Mud, controlling technical or architectural debt in generated code, designing APIs and invariants…
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.