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 sidiangongyuan/codex-skills-library --skill search-firstgit clone --depth 1 https://github.com/sidiangongyuan/codex-skills-libraryWrote 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/sidiangongyuan/codex-skills-library/search-first)<a href="https://agentmods.dev/skills/sidiangongyuan/codex-skills-library/search-first"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/search-first/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/sidiangongyuan/codex-skills-library/search-first"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/search-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 229 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00052 | $0.02417 |
| Opus 5.5 | $0.00021 | $0.00967 |
| Sonnet 5.5 | $0.00010 | $0.00483 |
| Haiku 4.5 | $0.00005 | $0.00242 |
Grade A, and why
search-first 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 1mo 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/search-first — Research Before You Code
Systematizes the "search for existing solutions before implementing" workflow.
Trigger
Use this skill when:
- Starting a new feature that likely has existing solutions
- Adding a dependency or integration
- The user asks "add X functionality" and you're about to write code
- Before creating a new utility, helper, or abstraction
Workflow
┌─────────────────────────────────────────────┐
│ 0. NEED + LOCAL REUSE GATE │
│ Inspect approved local implementations │
│ and results before external searching │
├─────────────────────────────────────────────┤
│ 1. RESEARCH DECISION │
│ Decide whether reuse, targeted lookup, │
│ or broader research is actually needed │
├─────────────────────────────────────────────┤
│ 2. TARGETED SEARCH (only when warranted) │
│ ┌──────────┐ ┌──────────┐ ┌──────────┐ │
│ │ Registry │ │ Tools / │ │ GitHub / │ │
│ │ / docs │ │ skills │ │ evidence │ │
│ └──────────┘ └──────────┘ └──────────┘ │
├─────────────────────────────────────────────┤
│ 3. EVALUATE │
│ Score candidates (functionality, maint, │
│ community, docs, license, deps) │
├─────────────────────────────────────────────┤
│ 4. DECIDE │
│ ┌─────────┐ ┌──────────┐ ┌─────────┐ │
│ │ Adopt │ │ Extend │ │ Build │ │
│ │ as-is │ │ /Wrap │ │ Custom │ │
│ └─────────┘ └──────────┘ └─────────┘ │
├─────────────────────────────────────────────┤
│ 5. IMPLEMENT │
│ Reuse approved solution or write the │
│ smallest justified custom code │
└─────────────────────────────────────────────┘
Decision Matrix
| Signal | Action |
|---|---|
| Approved local implementation or result | Reuse or repair — no broad fresh search required |
| Specific local gap or uncertainty | Targeted lookup — search only for that issue |
| New dependency, new mechanism, or uncertain external fact | Research — compare evidence before deciding |
| Exact match, well-maintained, MIT/Apache | Adopt — use directly when available or within authorized implementation scope |
| Partial match, good foundation | Extend — add a thin wrapper within authorized implementation scope |
| Multiple weak matches | Compose — combine 2-3 small packages |
| Nothing suitable found | Build — write custom, but informed by research |
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.
- 1mo ago Changed · +44 lines · -3 tokens per session fd455281a018
- 1mo ago First seen · 196 lines · 55 tokens per session scan A dcc35831f11b
search-first is a skill published in the GitHub repository sidiangongyuan/codex-skills-library (24 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 2,417 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
zeroplot
Create editable charts, diagrams, figures, posters, or slides from intent, data, or references.
paper-skill-name
Use when [trigger symptoms, user intents, task contexts]. Include Chinese trigger phrases when useful. Do not summarize workflow here.
nature-statistics
A guide for checking or writing how statistical analyses are reported in scientific papers submitted to Nature or similar high-impact journals.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
aiwg-regenerate-copilot
Regenerate copilot-instructions.md for GitHub Copilot with vendor-specific content only.
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.