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 agents/yogasw/wick/skills-managergit clone --depth 1 https://github.com/yogasw/wickWrote 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/agents/yogasw/wick/skills-manager)<a href="https://agentmods.dev/agents/yogasw/wick/skills-manager"><img src="https://agentmods.dev/badge/agents/yogasw/wick/skills-manager.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 | $0.00000 | $0.01691 |
| Opus 5 | $0.00000 | $0.00846 |
| Sonnet 5 | $0.00000 | $0.00338 |
| Haiku 4.5 | $0.00000 | $0.00169 |
Grade A, and why
skills-manager 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 4d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills Manager
The Skills Manager is a built-in UI for browsing, previewing, syncing, and deleting skill files (.md prompt files) across all agent skill directories on the host.
::: info Source
Core sync logic: internal/agents/skillsync/sync.go.
UI handler: internal/tools/agents/skills.go.
Templates: internal/tools/agents/view/skills.templ.
:::
What are skill directories?
Each AI CLI has its own skill folder on disk:
| Provider | Path |
|---|---|
| Claude Code | ~/.claude/skills/ |
| Codex | ~/.codex/skills/ |
| Gemini CLI | ~/.gemini/skills/ |
| Wick (built-in provider) | ~/.<app>/skills/ |
| Generic / shared | ~/.agents/skills/ |
Skills are plain .md files (or folders containing .md files) that the CLI loads as reusable instructions — slash commands, personas, workflow prompts, etc. Each provider has its own copy; keeping them in sync across providers is what this feature solves.
The wick directory is auto-created the first time skills are listed (so it always exists, even before any skill has been added) — wick is a first-class skill provider alongside the CLIs, not just a sync target. Because a wick session runs in-process rather than shelling out to a CLI, it doesn't load skills the same way: it injects a compact catalog (name, description, SKILL.md path) into its system prompt and reads a skill's full body on demand. See Providers → Skills.
claude and codex skip the hardcoded ~/.claude/~/.codex path in favor of $CLAUDE_CONFIG_DIR/$CODEX_HOME when either is set, since both env vars relocate the CLI's whole config tree (skills included).
Wick's shipped skills
A handful of how-to skills (connectors, plugins, workflows, agents) ship inside the wick binary and are extracted into the wick skills dir above on first use, alongside the user's own skills. They're marked Builtin in the API and carry a "MANAGED BY WICK" header — do not edit them, they're rewritten from the binary whenever they differ (compared by content hash, so unrelated files and unchanged shipped files keep their mtime and are left alone).
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.
- 4d ago First seen · 116 lines · 0 tokens per session scan A ac5b5d9e6b3c
skills-manager is an agent published in the GitHub repository yogasw/wick (5 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,691 tokens. 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 agents, from other repositories
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
cursor-rescue
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Cursor.
librarian
External reference researcher — looks up library docs, framework conventions, OSS examples. Read-only, no memory injection. (Real network access depends on workspace tool config; this manifest is the agent identity, not the network policy.).