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 1Milkdeliver/capsift --skill myskillsgit clone --depth 1 https://github.com/1Milkdeliver/capsiftWrote 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/1milkdeliver/capsift/myskills)<a href="https://agentmods.dev/skills/1milkdeliver/capsift/myskills"><img src="https://agentmods.dev/badge/skills/1milkdeliver/capsift/myskills.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 5.1 | $0.00072 | $0.00953 |
| Opus 5 | $0.00036 | $0.00477 |
| Sonnet 5 | $0.00014 | $0.00191 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
myskills 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 7d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/myskills
Use the language-selection rules from the sibling helpme skill, then render the matching
static catalog in references/locales/. Never translate stable menu text at runtime.
Resolve commands through the plugin-root menu-map.json; an absent command is explicitly
Unavailable via its * mapping. Never infer that the optional full CLI is installed merely
because the bundled MCP search/load runtime is available.
Interaction
- Bare
/myskills: render both visible groups and all items. Provider, Routing, Inventory, Lifecycle, Risks, and Conflicts are never hidden. Append the catalog'snavigationitems so language settings and the CapSift main menu stay visible. list/inventory: callcapability.searchwith an empty query and a bounded result. Setinclude_inventory: true,include_cards: true, andkinds: ["skill"]. Useinventory.active_by_kind.skillfor the global active Skill total and query-leveltotal_matchesfor the current filter instead of counting cards. Return at most five Skill cards unless the user asks for more. Show the generation/status compactly and report only non-zero safe diagnostic counts.- Accept the visible number only while the My Skills menu is the active interaction.
- Accept exact commands and aliases:
find,list/ls,loaded/using,show/info,providers,routing/why,lifecycle,risks,conflicts/check. /myskills backreturns to the My Skills menu./helpme homealways returns to the CapSift main menu, and/helpme languageopens language settings. Recognize localized返回上一级,返回主菜单,back, andhomeonly while this menu is active.- Append the catalog's
navigationitems exactly once after every My Skills result. - Recognize explicit natural-language intents such as “帮我找一个处理 PDF 的 Skill”, “我加载了哪些 Skill”, or “为什么选择 documents”. Use low reasoning for status, listing, and direct commands; use medium reasoning only when task-to-Skill matching is ambiguous.
- Never intercept native
/help,/skills,/status,/model, or/mcpcommands. - Do not trigger on source code, documentation, or casual text that merely contains the word “skill”.
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.
- 7d ago First seen · 64 lines · 72 tokens per session scan A b8fcc9941b55
myskills is a skill published in the GitHub repository 1Milkdeliver/capsift (0 stars, last pushed 24d ago), licensed MIT. It adds 72 tokens to every session and 953 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…