Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add haabe/mycelium/plugin install 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/haabe/mycelium/migrate-from-legacy)<a href="https://agentmods.dev/skills/haabe/mycelium/migrate-from-legacy"><img src="https://agentmods.dev/badge/skills/haabe/mycelium/migrate-from-legacy/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/haabe/mycelium/migrate-from-legacy"><img src="https://agentmods.dev/badge/skills/haabe/mycelium/migrate-from-legacy.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 | $0.00086 | $0.02817 |
| Opus 5 | $0.00043 | $0.01409 |
| Sonnet 5 | $0.00017 | $0.00563 |
| Haiku 4.5 | $0.00009 | $0.00282 |
Grade A, and why
migrate-from-legacy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate from legacy to plugin form
When this skill runs, walk the user through moving from legacy install to plugin install. The migration is non-destructive to project state: canvas, diamonds, memory, decision log, evals, and active metrics are preserved. Only framework reference content (skills, hooks, engine, scripts, schemas, etc.) is removed from .claude/ — that content now ships in the plugin cache.
Step 1: Detect current install form
Check the project's .claude/ directory:
test -d "$CLAUDE_PROJECT_DIR/.claude/skills" && echo "legacy framework files present" || echo "no legacy framework files"
test -d "$CLAUDE_PROJECT_DIR/.claude/canvas" && echo "project state present" || echo "no project state"
Three states:
- Legacy install (skills/ + canvas/ both present): proceed to Step 2.
- Already migrated (canvas/ present, skills/ absent): tell the user "This project is already on plugin form. No migration needed." and exit.
- Empty (neither present): tell the user "No Mycelium install detected. Run
/mycelium:startto bootstrap a fresh plugin install." and exit.
Step 2: Verify the plugin is installed
Ask the user to confirm the plugin is installed before deleting legacy framework files. If they don't have the plugin yet, deleting framework files would leave them with no Mycelium at all.
Tell them to run inside Claude Code:
/plugin marketplace add haabe/mycelium
/plugin install mycelium@haabe-mycelium
Then ask: "Is the plugin installed now?" Wait for confirmation before continuing. Acceptable answers: "yes", "installed", "done", or running /mycelium:ping to verify the plugin loaded (returns a deterministic marker if so).
If the user says no or seems uncertain, exit and tell them to come back after installing.
Step 3: Verify a clean working tree
The migration is reversible via git, so the project must be a git repo with a clean working tree before proceeding. Run:
cd "$CLAUDE_PROJECT_DIR"
git rev-parse --is-inside-work-tree # must succeed
git diff-index --quiet HEAD -- # must succeed (no uncommitted changes)
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.
- 9d ago First seen · 201 lines · 86 tokens per session scan A 45025a35cb9f
migrate-from-legacy is a skill published in the GitHub repository haabe/mycelium (45 stars, last pushed 2d ago), licensed MIT. It adds 86 tokens to every session and 2,817 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 2026-08-30.
Other skills, from other repositories
skill-finder
Find the right Affitor skill for your goal. Triggers on: "which skill should I use", "find me a skill", "what skills are available", "help me choose a skill", "skill for SEO", "skill for email", "explore skills", "I'm new to Affitor", "what can Affitor do", "search skills", "skill for blog writing", "skill for landing…
meraki-network-ops
Cisco Meraki organization and network operations (read-only) — org discovery, network inventory, device inventory, clients, group policies, admins, licensing, alert settings via Cisco's official Meraki MCP. Use as the entry point for any Meraki question, to discover org and network IDs, or to inventory Meraki networks…
auto
Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. Classifies a plain-English goal and routes it to the right specialist skill. Routing is never overhead, so use it even when the target skill seems obvious; skip only when already executing inside another…
gingiris-user-interview
A playbook for interviewing users and operating an early product launch, including screening participants, running interviews, testing beta versions, and reviewing churn. It is based on a described process for finding product-market fit, meaning a product consistently meeting a real user need.
tao-setup
One-time session setup and orchestration map for the TAO skill bank. Run this first when the TAO skills were installed individually (e.g. from a public skills catalog) so the session gets the cross-skill discovery flow, credential checks, and host preflight that the bundled plugin hook would otherwise inject…
tao-list-capabilities
Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when the user asks "what can TAO Skill Bank do", "list TAO models", "which TAO workflows are available", or "what supports AutoML".