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/lyhcode/agent-skills/1password-clinpx skills add lyhcode/agent-skills --skill 1password-cligit clone --depth 1 https://github.com/lyhcode/agent-skillsWhat 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 | $0.00128 | $0.01731 |
| Opus 5 | $0.00064 | $0.00865 |
| Sonnet 5 | $0.00026 | $0.00346 |
| Haiku 4.5 | $0.00013 | $0.00173 |
Grade C, and why
1password-cli scanned grade C 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 yesterday.
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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
op run --no-masking -- printenv DB_PASSWORD How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1Password CLI (op) Assistant
Help users manage 1Password secrets and items using the op CLI.
Prerequisites
- The
opCLI must be installed (brew install 1password-clion macOS) - Desktop app integration must be enabled (1Password app > Settings > Developer > Integrate with 1Password CLI)
- Verify setup:
op whoami
Security Principles
Secrets that leak into terminal output, shell history, or version-controlled files are hard to revoke and easy to miss. These guidelines reduce that surface area:
- Avoid printing raw secrets unless the user explicitly asks. Prefer
op read --out-fileorop runto keep secrets out of scrollback and logs. - Use
--format=jsonfor list/get commands — structured output is easier to parse and less likely to be misread. - Use JSON templates when creating/editing items with sensitive values. Inline assignment statements (
'password=...') can appear inpsoutput on shared machines. - Prefer
op://references over reading secrets into shell variables. References are resolved just-in-time and never persist in memory. - Keep secrets out of version control. Don't write resolved values to files that might be committed. Use
.envfiles withop://references instead. - Delete template files after use — they contain resolved secrets on disk.
Reference Files
This skill includes two reference files for detailed lookups. Consult them as needed:
| File | When to use |
|---|---|
| reference/commands.md | Looking up specific flags, subcommands, field assignment syntax, or shell completion setup |
| reference/conventions.md | Deciding item categories, naming items, organizing vaults, choosing field types, Markdown syntax limits in notes, or reviewing the best-practices checklist |
Secret References (op://)
The op:// URI is the core abstraction — it points to a secret without exposing it:
op://<vault>/<item>/[<section>/]<field>[?<query>]
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.
- yesterday First seen · 192 lines · 128 tokens per session scan C 6800381434aa
1password-cli is a skill published in the GitHub repository lyhcode/agent-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 128 tokens to every session and 1,731 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…