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 krapie/mycelium --skill clipgit clone --depth 1 https://github.com/krapie/myceliumWrote 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/krapie/mycelium/clip)<a href="https://agentmods.dev/skills/krapie/mycelium/clip"><img src="https://agentmods.dev/badge/skills/krapie/mycelium/clip/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/krapie/mycelium/clip"><img src="https://agentmods.dev/badge/skills/krapie/mycelium/clip.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00038 | $0.00303 |
| Opus 5.5 | $0.00015 | $0.00121 |
| Sonnet 5.5 | $0.00008 | $0.00061 |
| Haiku 4.5 | $0.00004 | $0.00030 |
Grade A, and why
clip 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.
What it actually says
Clip to Mycelium
The user's message that invoked this skill is the request. What they wrote with $clip are the arguments: [N | pick] [note].
-
First run this shell command, which lists the recent answers before the request with their turn numbers:
mycelium clip add --here --list --skip-request
-
Pin by running
mycelium clip add --here --turn <turn or range> --note "<note>". Use only turn numbers from that list, never guessed ones. Leave out--notewhen there is no note, and quote the note safely.- No arguments, or only a note: pin the newest answer.
- A number N first (e.g.
3 note): pin the last N turns ending at the newest answer, using the range form the list's last line gives. pickfirst: show the user the list as a short numbered list, ask which turn or range to pin, and run nothing until they answer.
-
Tell the user in one line what was clipped: the id and the preview line.
If a command fails, show its error as it is. Do not retry with a session id you guessed. Do nothing else.
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 · 23 lines · 38 tokens per session scan A 18acc3e23dad
clip is a skill published in the GitHub repository krapie/mycelium (42 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 303 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 2026-10-24.
Other skills, from other repositories
live-transcript-summary
A real-time note-taking skill that watches audio transcription in the current WPS note and periodically organizes it. WPS is an office and note-taking application.
tag-organize-cli
A command-line workflow for organizing file-level tags in WPS Notes, a cloud note-taking service. It uses the wpsnote-cli program and does not require an MCP server connection.
content-digest
A skill for turning supplied material into structured knowledge notes and saving them to WPS Notes, a note-taking service.
note-calendar
A macOS workflow connecting WPS Notes with the system Calendar. It can query, create, move, and delete calendar events, and link notes and calendar items in both directions.
tag-organize
A workflow for organizing file-level tags in WPS Notes, a cloud note-taking service. It uses note statistics, tag searches, note details, note searches, and tag-management tools.
query
Answer questions about the wiki by searching, reading, and synthesizing relevant scraps with [[Title]] citations. Use this when the user wants to query the wiki, ask what they have written about a topic, compare scraps, find related notes, or pull a synthesized overview from existing scraps.