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 dihannahdi/mycelium --skill mycelium-foragegit clone --depth 1 https://github.com/dihannahdi/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/dihannahdi/mycelium/mycelium-forage)<a href="https://agentmods.dev/skills/dihannahdi/mycelium/mycelium-forage"><img src="https://agentmods.dev/badge/skills/dihannahdi/mycelium/mycelium-forage/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/dihannahdi/mycelium/mycelium-forage"><img src="https://agentmods.dev/badge/skills/dihannahdi/mycelium/mycelium-forage.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 | $0.00200 | $0.02880 |
| Opus 5 | $0.00100 | $0.01440 |
| Sonnet 5 | $0.00040 | $0.00576 |
| Haiku 4.5 | $0.00020 | $0.00288 |
Grade A, and why
mycelium-forage 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 10d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mycelium — Foraging for Context
You are investigating a data problem through DataHub, and the constraint you are working under is context, not access. You can reach every entity in the catalogue. You cannot afford to read them.
This skill gives you a discipline for acquiring only what the question needs, and a set of tools that make that discipline measurable.
Multi-Agent Compatibility
Works across Claude Code, Cursor, Codex, Copilot, Gemini CLI, and Windsurf.
What works everywhere: the whole foraging workflow, via the mycelium MCP server or the
mycelium CLI.
Claude Code-specific: allowed-tools in the frontmatter above. Everything else is plain
tool calls.
Requires the Mycelium MCP server. Either point it at a running DataHub:
claude mcp add mycelium \
-e MYCELIUM_BACKEND=live \
-e DATAHUB_GMS_URL="http://localhost:8080" \
-e DATAHUB_GMS_TOKEN="<token>" \
-- uvx --from mycelium-datahub mycelium-mcp
…or run it offline against the bundled showcase-ecommerce snapshot by omitting the
DataHub variables. The snapshot is real DataHub metadata, so the workflow below is identical
either way.
Not This Skill
| If the user wants to... | Use this instead |
|---|---|
| Find an entity by keyword or metadata | /datahub-search |
| Trace lineage they already know the shape of | /datahub-lineage |
| Add or change metadata (descriptions, tags, owners) | /datahub-enrich |
| Create assertions or manage incidents | /datahub-quality |
| Configure the DataHub connection | /datahub-setup |
Key boundary: /datahub-lineage answers "what feeds into X?" — you name the entity and
it walks the graph. Mycelium answers "which handful of the ten thousand things in here
actually explain this symptom?" — you name the symptom, and it decides where to walk and
how much of each node to read. Reach for /datahub-lineage when you know the entity; reach
for this when you know only the problem.
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.
- 10d ago First seen · 266 lines · 200 tokens per session scan A dd02aa347939
mycelium-forage is a skill published in the GitHub repository dihannahdi/mycelium (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 200 tokens to every session and 2,880 once invoked, about $0.0010 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
datahub-verified-remediation
Use this skill when a source schema change has broken, or is about to break, a downstream transformation and the user wants a fix they can merge — not a summary. Triggers on: "a column was renamed, fix the dbt model", "this field is gone downstream", "schema drift", "our model still selects the old column", "generate…
known-path
Use when answering business metric questions from a data catalog, generating SQL that must use Finance-canonical tables, or when an agent might thrash search and pick a similarly named deprecated table. Loads a short route sheet, lights only trusted assets, fails closed on bad trust, writes the route back.
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.