mycelium

mycelium is a skill for Claude Code, Codex from tdimino/claude-code-minoan. It costs 34 tokens per session (890 once invoked), scanned A, original, MIT.

A file-level memory system that stores notes in Git, the version-control system used to track code changes. Agents read notes before editing files and leave notes about decisions, context, warnings, and other useful knowledge afterward.

In plain words
What is it for?
Use it to record why code was designed a certain way, what a file does, project constraints, warnings, observations, and follow-up work.
Why use it?
It keeps important project knowledge attached to the code instead of losing it between sessions or agents. This reduces repeated investigation and helps avoid known fragile areas.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to record why code was designed a certain way, what a file does, project constraints, warnings, observations, and follow-up work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tdimino/claude-code-minoan/mycelium
Install

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.

Any agent
npx skills add tdimino/claude-code-minoan --skill mycelium
Clone the repo
git clone --depth 1 https://github.com/tdimino/claude-code-minoan

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mycelium

README.md
[![agentmods](https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/mycelium/github.svg)](https://agentmods.dev/skills/tdimino/claude-code-minoan/mycelium)
Your own site
<a href="https://agentmods.dev/skills/tdimino/claude-code-minoan/mycelium"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/mycelium/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.

agentmods 80×15 button for mycelium

Your own site · 80×15
<a href="https://agentmods.dev/skills/tdimino/claude-code-minoan/mycelium"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/mycelium.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 890 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.00890
Opus 5 $0.00017 $0.00445
Sonnet 5 $0.00007 $0.00178
Haiku 4.5 $0.00003 $0.00089

Measured 8d ago against content hash 7d24a97211af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mycelium 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 8d 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.

skills/integration-automation/mycelium/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mycelium — Daimonic Spores

Structured notes attached to git objects via refs/notes/mycelium. Notes are daimonic spores—fragments of soul essence shed by the agent that wrote them.

Before working on a file, check for its note. After meaningful work, leave a note.

On Arrival

mycelium.sh find constraint   # project principles & rules
mycelium.sh find warning      # known fragile things
mycelium.sh context <file>    # everything known about it

After Work

mycelium.sh note <file> -k <kind> --slot <your-name> -m "<insight>"
mycelium.sh note HEAD -k context -m "What I did and why."

Kinds

Kind When to use
decision Why something was chosen—rationale that outlives the commit message
context Background needed before touching this code
summary What a file or module does
warning Fragile areas, footguns, non-obvious breakage
constraint Hard rules—must be retryable, must not depend on X
observation Something noticed but not yet acted on
value Cultural principles—guides judgment
todo Planned work—compost when done

Subdaimon Slots

Each subdaimon writes to its own slot to preserve identity:

mycelium.sh note src/auth.rs -k warning --slot bohen -m "Race condition in token refresh."
mycelium.sh note src/auth.rs -k decision --slot demiurge -m "Used mutex over channel."

context aggregates all slots. read --slot <name> reads one.

Quality Gates

Before writing a note, validate:

  1. Novelty: Does a similar note already exist? (mycelium.sh read <file>)
  2. Specificity: Is this about this file or the whole project? (Project-level → mycelium.sh note .)
  3. Durability: Will this matter in 2 weeks? (Ephemeral → working memory, not mycelium)
  4. No secrets: No API keys, tokens, passwords, or PII

Composting

Notes go stale when files change. Compost after meaningful work:

mycelium.sh compost <file> --dry-run    # see what's stale
mycelium.sh compost <oid> --compost     # absorb and archive
mycelium.sh compost <oid> --renew       # still true, re-attach

Read the full file on GitHub · 100 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 8d ago First seen · 100 lines · 34 tokens per session scan A 7d24a97211af

Subscribe to this mod's changes

mycelium is a skill published in the GitHub repository tdimino/claude-code-minoan (41 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 890 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

gh-issues

Use when creating, searching, updating, or managing GitHub issues via CLI. Triggers: "issue", "create issue", "gh issue", "task tracking", "context", "handoff", "resume task", "session context", "save progress", "active tasks", "in-progress", "my tasks", "open issues". Covers: gh commands, bulk operations, JSON/jq…

serejaris/personal-corp-os · 104 tokens

memory-commit

Use when the user explicitly says "remember this", "save this", "ghi nho", "luu lai", "save for next time", or otherwise asks to persist the immediately preceding context. Captures with the appropriate contexttype (decision, preference, fact, skill, task, conversation) so future sessions can retrieve it accurately.

n24q02m/mnemo-mcp · 72 tokens

safe-public-release

Use when publishing, open-sourcing, exporting, sanitizing, or moving code, agent skills, prompts, templates, fixtures, datasets, workshop assets, or other artifacts from a private repository, vendor/runtime environment, or mixed working directory into a public repository or registry. Builds a provenance inventory…

serejaris/personal-corp-os · 166 tokens

wiki-retrieve

Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…

AgriciDaniel/claude-obsidian · 81 tokens

vellum-memory-v3-migration

One-time migration of an existing memory-v2 concept corpus into the memory-v3 section-grain "wiki" — topical articles with a stand-alone lead and queryable sections — with loss-proof staging, assistant-reviewed authoring, and a retrieval-eval gate before cutover.

vellum-ai/vellum-assistant · 63 tokens

release

CONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release. Use when shipping a new plugin version. NOT distributed.

oliver-kriska/claude-elixir-phoenix · 60 tokens