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/usemycontext/claude-code-plugin/umcnpx skills add usemycontext/claude-code-plugin --skill umcgit clone --depth 1 https://github.com/usemycontext/claude-code-pluginWhat 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 | $0.00061 | $0.01433 |
| Opus 5 | $0.00030 | $0.00717 |
| Sonnet 5 | $0.00012 | $0.00287 |
| Haiku 4.5 | $0.00006 | $0.00143 |
Grade A, and why
umc 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 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.
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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UseMyContext in Claude Code
UseMyContext (usemycontext.ai) hosts your personal context and serves it to any AI client over MCP. This plugin registers the UseMyContext MCP server, so once you sign in, Claude Code can read your profile, list and open your files, and answer from your documents. Everything is read-only against your files and audited.
Each of your UseMyContext projects has its own context and its own @handle. This skill lets you map a
folder to one project, so a work repo reads your work profile and a side project reads your personal one.
Consult UseMyContext proactively
Whenever a question touches the user personally - their background, work, history, projects, or
documents - check the UseMyContext profile and ask_docs tools before saying you do not know or
guessing. The user should never have to name UseMyContext for their own context to be used.
Close the loop: offer to save what the session taught
When a conversation has surfaced something new and durable about the user and is wrapping up (the user
says thanks, goodbye, or that's all, or the task completes), offer to save it with suggest_update
before the context is lost. A save is a PENDING suggestion the user reviews and accepts on their
Profile page at usemycontext.ai, and nothing is ever written to their files.
Status: which profile is this folder using
- Look for a
.umcfile in the project root (the directory Claude Code was started in). - If
.umcexists, read itsprojectIdand optionalhandleand report the mapping plainly, for example:This folder is mapped to your "@work" context (p2). - If there is no
.umcfile, tell the user this folder has no mapping, so UseMyContext tool calls read their account's active profile. Offer to create a mapping.
The .umc file is a small key=value file:
projectId=p2
handle=@work
A projectId may only be letters, digits, _ and -, up to 32 characters, and a handle only @
followed by letters, digits and -, up to 40. Anything else and the whole marker is ignored, so a
repository you did not write cannot use one to talk to your assistant.
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 · 107 lines · 61 tokens per session scan A c775dc1d1143
umc is a skill published in the GitHub repository usemycontext/claude-code-plugin (1 stars, last pushed 8d ago), licensed MIT. It adds 61 tokens to every session and 1,433 once invoked, about $0.0003 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
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约，产出 UI-DESIGN.md。四端通用。.
taiyi-evolve
TaiyiForge 辅助 — 实现后架构与文档同步（architecture-sync）。OpenCode / Claude / Codex / Cursor 通用。.
taiyi-diagram-c4
TaiyiForge 辅助 — 从代码反推 C4 架构文档（Observed/Inferred 分层 · Mermaid 真源）。OpenCode / Claude / Codex / Cursor 通用。.
writing-style
Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.
steer
Project-profile recalibration. Audits session calibration drift, presents per-cluster evidence for a user verdict, writes the updated project-profile rule, and inscribes a settled-direction clause.
maestro-verify
Verify and close - cross-check coverage, run the VERIFY table, deliver the verdict, harvest durable lessons into decisions, close the bundle, and never claim remote state from local evidence.