Agent skill

Mycelium

Hidden layer of structured git notes for agent collaboration.

MITAuto-check passedDevelopment

Install Mycelium

skills CLI

$ npx skills add openprose/mycelium --skill mycelium -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install openprose/mycelium mycelium --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "mycelium" agent skill from https://github.com/openprose/mycelium/tree/main into .claude/skills/mycelium/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mycelium", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add openprose/mycelium --skill mycelium -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install openprose/mycelium mycelium --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "mycelium" agent skill from https://github.com/openprose/mycelium/tree/main into .agents/skills/mycelium/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mycelium", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add openprose/mycelium --skill mycelium -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install openprose/mycelium mycelium --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "mycelium" agent skill from https://github.com/openprose/mycelium/tree/main into .cursor/skills/mycelium/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mycelium", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add openprose/mycelium --skill mycelium -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install openprose/mycelium mycelium --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "mycelium" agent skill from https://github.com/openprose/mycelium/tree/main into .gemini/skills/mycelium/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mycelium", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install openprose/mycelium mycelium

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add openprose/mycelium --skill mycelium -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "mycelium" agent skill from https://github.com/openprose/mycelium/tree/main into .github/skills/mycelium/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mycelium", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add openprose/mycelium --skill mycelium -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install openprose/mycelium mycelium --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "mycelium" agent skill from https://github.com/openprose/mycelium/tree/main into .opencode/skills/mycelium/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mycelium", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: mycelium
GitHub stars: 123
Token cost: ~2.4k tokens
SKILL.md length: 611 words
Files: 51 (incl. scripts)
Skills in repo: 1
Repo updated: Apr 10, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Hidden layer of structured git notes for agent collaboration.

Tasks that involve Git workflow
SKILL.md covers On arrival, Core commands, Workflow scripts in this repo and Patterns, plus 8 more sections
Runs Shell scripts from its folder; calls git and kind

What it does

Mycelium is an agent skill from openprose/mycelium. Hidden layer of structured git notes for agent collaboration. When working in any git repo, check for notes on objects you touch before acting, and leave notes after meaningful work. Uses git notes directly — helper script and workflow scripts included.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 55 other files, including scripts (for example `.claude-plugin/marketplace.json`, `.github/workflows/ci.yml` and `CHANGELOG.md`).

It sits in Development, covering Git workflow. It works with Git. The licence is MIT.

When your agent uses it

Tasks that involve Git workflow

Example prompts

“/mycelium”

Requirements

A Bash shell

What it can do on your machine

Read from SKILL.md and the folder at commit a58b8c9. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Shell, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
- git
- kind
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mycelium loads about 2.4k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 611 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~66
When it runs · the whole SKILL.md, loaded when a task matches: ~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from openprose/mycelium at commit a58b8c9, republished under its MIT licence (© openprose). 611 words, ~2,360 tokens.

Download SKILL.mdSave it as .claude/skills/mycelium/SKILL.md (or your agent's skills folder). This skill also uses 50 other files; get the full folder from GitHub.

name: mycelium
description: Hidden layer of structured git notes for agent collaboration. When working in any git repo, check for notes on objects you touch before acting, and leave notes after meaningful work. Uses git notes directly — helper script and workflow scripts included.

Mycelium

Structured notes attached to git objects via refs/notes/mycelium.

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

That’s the whole contract. Mycelium is the storage layer. Richer arrival / history workflows can live in skill scripts.

On arrival

Start every session with:

bash

mycelium.sh find constraint                 # project principles & rules
mycelium.sh find warning                    # known fragile things
scripts/context-workflow.sh <file>          # recommended arrival workflow (repo checkout)

If you only have the runtime file and not this repo checkout, do the same workflow manually:

bash

mycelium.sh read <file>                     # exact note on current object
mycelium.sh read HEAD                       # current commit note
# plus raw git notes show on parent dirs / root as needed

Before leaving:

bash

mycelium.sh note HEAD -k context -m "What I did and why."
mycelium.sh note <changed-file> -k <kind> -m "What future agents should know."

If you made a decision, use kind decision and add a tested-by edge to the test that validates it. If you found something fragile, use kind warning.

Core commands

Use these as the protocol-ish primitives:

bash

mycelium.sh note [target] -k <kind> -m <body>   # write
mycelium.sh read [target]                        # read exact note on current object
mycelium.sh follow [target]                      # read + resolve edges
mycelium.sh refs [target]                        # inbound references
mycelium.sh find <kind>                          # search by kind
mycelium.sh kinds                                # vocabulary in use
mycelium.sh list                                 # all annotated objects
mycelium.sh branch [use|merge] [name]            # branch-scoped notes
mycelium.sh doctor                               # graph facts
mycelium.sh dump                                 # everything, greppable

Workflow scripts in this repo

These are recommended workflows, not part of the core CLI:

bash

scripts/context-workflow.sh <path> [ref]                    # current file + parent dirs + current commit
scripts/path-history.sh <path> [ref]                        # older file notes via git history
scripts/note-history.sh <target>                            # note overwrite history via notes ref
scripts/compost-workflow.sh [path|oid] [--compost|--renew]  # explicit stale/renew workflow

Use them when you want richer context, but keep in mind they are recipes built on top of git + mycelium primitives.

Rule of thumb:

context-workflow.sh = default arrival workflow for a path
path-history.sh = explicit historical notes for a file
note-history.sh = overwrite history for one note target
compost-workflow.sh = opt-in stale/renew lifecycle for repos that still want it

If a repo still wants an explicit stale/renew lifecycle, use scripts/compost-workflow.sh. The simpler default is to use git-native history first and write a fresh current note when older context still matters.

Patterns

Three patterns cover most usage.

Pattern 1: One ref accumulates many notes

A file can collect notes from different agents over time.

bash

mycelium.sh note src/auth.ts -k summary -m "Handles OAuth2 refresh flow."
mycelium.sh note src/auth.ts -k warning -m "Token refresh has a race condition."
mycelium.sh refs src/auth.ts

When you need older notes on that file, use git history rather than a special core lifecycle command:

bash

scripts/path-history.sh src/auth.ts

Pattern 2: One note connects many refs

A single note can link to multiple objects via edges.

bash

mycelium.sh note SKILL.md -k decision -t "Packaged as an agent skill" \
  -e "depends-on blob:$(git rev-parse HEAD:README.md)" \
  -m "The skill teaches agents the convention on-demand."

mycelium.sh follow SKILL.md

Use this whenever a note’s meaning involves more than one object.

Pattern 3: Planning graph

Use depends-on edges to structure planned work.

bash

mycelium.sh note src/auth.ts -k context -t "Planned: fix race condition" \
  -m "Need mutex around token refresh. See warning note."

mycelium.sh note src/http.ts -k context -t "Planned: retry after refresh" \
  -m "HTTP client should retry once after auth refresh."

mycelium.sh note HEAD -k context -t "Plan: auth hardening" \
  -e "depends-on blob:$(git rev-parse HEAD:src/auth.ts)" \
  -e "depends-on blob:$(git rev-parse HEAD:src/http.ts)" \
  -m "Two files need coordinated changes."

Check for notes

bash

mycelium.sh read path/to/file.ts              # exact note on current object
mycelium.sh follow HEAD                       # note + where its edges lead
mycelium.sh refs path/to/file.ts              # all notes pointing at target
mycelium.sh find decision                     # all decisions
mycelium.sh find constraint                   # all constraints
git log --notes=mycelium --oneline -20        # recent commits with notes

Or with raw git:

bash

git notes --ref=mycelium show $(git rev-parse HEAD:path/to/file.ts) 2>/dev/null
git notes --ref=mycelium show HEAD 2>/dev/null

Leave notes

bash

mycelium.sh note -k context -m "Why I did this."                     # HEAD
mycelium.sh note path/to/file.ts -k summary -m "What this does."     # file
mycelium.sh note src/auth/ -k constraint -m "Must be retryable."     # directory
mycelium.sh note . -k value -m "Project-level principle."            # project
mycelium.sh note -k decision -t "Use YAML" -m "Needs comments."     # decision

Target stability

Every target has different stability.

Target	Stable?	Use when
`path/to/file`	✓ findable by path even if file changes	Note is about the file
`$(git rev-parse HEAD:file)`	pinned to this exact blob OID	Note is about this specific version
`.`	✓ project-level, always findable	Note applies to the whole repo
`HEAD`	pinned to commit OID (jj: survives via change_id)	Note is about this change
`src/dir/`	✓ findable by path	Note is about the module

Default: use paths. Most notes are about files, not specific versions. The path edge keeps them findable. Use raw OIDs only when you mean “this exact content.”

Show full SKILL.md (221 more words)Show less

Note format

text

kind decision
title Short label
edge explains commit:abc123...
edge targets-path path:src/auth/retry.ts

Free-form body. Markdown encouraged.

Headers: kind (required), edge, title, status

Kinds: decision · context · summary · warning · constraint · observation · value · todo — or invent your own.

Edge types: explains · applies-to · depends-on · warns-about · targets-path · targets-treepath — or invent your own.

Targets: commit:<oid> · blob:<oid> · tree:<oid> · path:<filepath> · note:<oid>

Note history

There is no special supersedes chain in the note body. Overwrite history lives in git itself on the notes ref.

bash

scripts/note-history.sh path/to/file.ts

Or raw git:

bash

OID=$(git rev-parse HEAD:path/to/file.ts)
FANOUT="${OID:0:2}/${OID:2}"
git log -p refs/notes/mycelium -- "$FANOUT"

Historical notes for a file

If you want older notes on a file path, use git history:

bash

scripts/path-history.sh src/auth.ts

If an older note still matters, write a fresh current note that carries forward the relevant insight.

Slots

Multiple tools or agents can write notes on the same object without obliteration. Each slot is a named lane backed by its own notes ref.

bash

mycelium.sh note src/auth.ts --slot skeleton -k observation -m "Structure."
mycelium.sh note src/auth.ts --slot enricher -k summary -m "Context."
mycelium.sh read src/auth.ts --slot skeleton

Rules:

read / follow use the default slot unless --slot is given
find / kinds / doctor / prime aggregate all slots
Reserved names: main, default

Setup (once per clone)

bash

mycelium.sh activate        # notes visible in git log
mycelium.sh sync-init       # notes travel with fetch/push
mycelium.sh repo-id init    # durable repo identity
mycelium.sh zone init       # confidentiality zone
mycelium.sh export f -a internal
mycelium.sh export --all --audience internal      # batch export all notes
mycelium.sh export --all --kind decision -a public # batch export by kind
mycelium.sh import remote --as lib
mycelium.sh list-imports                          # show imported repos

jj+git colocated repos

If .jj/ is detected, mycelium adapts automatically — no flags needed. Commit notes get a targets-change edge (stable across jj rewrites). read falls back to change_id lookup when the commit OID changes. Prefer notes on files over commits — blob OIDs survive rewrites, commit OIDs don’t.

When jj rewrites commits (amend, rebase, squash), notes on old OIDs become orphaned. Use migrate to bulk-reattach them:

bash

mycelium.sh migrate --dry-run
mycelium.sh migrate
mycelium.sh migrate --map mapping.txt

Run mycelium.sh help for jj-specific guidance.

Files

SKILL.md and 50 other files (scripts) in the repository root of openprose/mycelium.

SKILL.md
.claude-plugin/marketplace.json
.github/workflows/ci.yml
.gitignore
.gitleaks.toml
CHANGELOG.md
DEVELOPING.md
LICENSE
PLUGIN-SPEC.md
README.md
demo/run-comparison.sh
hooks/post-checkout
hooks/post-commit
hooks/pre-commit
hooks/pre-push
hooks/reference-transaction
… and 35 more

Open the folder on GitHubat commit a58b8c9

Compare with similar skills

Mycelium next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Mycelium compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Mycelium this skillopenprose/mycelium	123	—	~2.4k	Automated safety check: Pass	MIT	6 mo ago
Finishing a Development Branchobra/superpowers	296k	5 repos	~1.9k	Automated safety check: Pass	MIT	today
Code Design Rationale Investigatorcursor/plugins	10k	9 repos	~2.6k	Automated safety check: Pass	None	today
Contributor-First PR MergeHKUDS/OpenHarness	16k	1 repos	~847	Automated safety check: Pass	MIT	4 mo ago
Migrate Internal Package into GhostTryGhost/Ghost	55k	—	~3.8k	Automated safety check: Pass	MIT	today
Create Pull Requestcline/cline	70k	1 repos	~1.6k	Automated safety check: Pass	Apache-2.0	today

Similar skills

Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
296k GitHub starsUsed in 5 repos~1.9k tokens
DevelopmentAuto-check passed
Code Design Rationale Investigator
cursor/plugins
Official
Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.
10k GitHub starsUsed in 9 repos~2.6k tokens
DevelopmentAuto-check passed
Contributor-First PR Merge
HKUDS/OpenHarness
Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.
16k GitHub starsUsed in 1 repo~847 tokens
DevelopmentAuto-check passed
Migrate Internal Package into Ghost
TryGhost/Ghost
Moves a package from another TryGhost repository into Ghost as an internal workspace package while keeping its Git history, with checkpoints for the steps that need an administrator.
55k GitHub stars~3.8k tokensUpdated today
DevelopmentAuto-check passed
Create Pull Request
cline/cline
Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.
70k GitHub starsUsed in 1 repo~1.6k tokens
DevelopmentAuto-check passed
Git Merge Conflict Resolver
tailcallhq/forgecode
Resolves Git merge conflicts with a plan-first workflow that keeps both sides' intent, regenerates lock files and backs up deleted-but-modified files.
7.6k GitHub starsUsed in 1 repo~4.5k tokens
DevelopmentAuto-check passed

Works with

Questions about Mycelium

What does Mycelium do?

Hidden layer of structured git notes for agent collaboration. Mycelium is an agent skill from openprose/mycelium. Hidden layer of structured git notes for agent collaboration.

When should I use Mycelium?

Mycelium fits situations like: tasks that involve Git workflow.

How do I install Mycelium in Claude Code?

Run `npx skills add openprose/mycelium --skill mycelium -a claude-code`. Or copy the skill folder (the openprose/mycelium repository) into .claude/skills/mycelium in your project. Claude Code loads it when a task matches its description.

How do I install Mycelium in Codex?

Run `npx skills add openprose/mycelium --skill mycelium -a codex`. Or copy the skill folder (the openprose/mycelium repository) into .agents/skills/mycelium in your project. Codex loads it when a task matches its description.

Can I use Mycelium in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openprose/mycelium --skill mycelium -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mycelium, .gemini/skills/mycelium, .github/skills/mycelium and .opencode/skills/mycelium in your project.

What does Mycelium need to run?

Going by SKILL.md and its folder, Mycelium needs a shell for the scripts in its folder and the command-line tools its instructions call (git and kind). Our summary lists: A Bash shell.

Does Mycelium access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Mycelium safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Mycelium use?

Mycelium is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Mycelium use?

About 2.4k tokens (SKILL.md is roughly 9.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Mycelium?

Skills that share tags, products or a category with Mycelium: Finishing a Development Branch (obra/superpowers, 296k stars), Code Design Rationale Investigator (cursor/plugins, 10k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars) and Migrate Internal Package into Ghost (TryGhost/Ghost, 55k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mycelium?

openprose (a GitHub organization) maintains it in openprose/mycelium, which has 123 GitHub stars. The repository was last updated on April 10, 2026.

Source: openprose/mycelium on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Mycelium

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Mycelium

On arrival

Core commands

Workflow scripts in this repo

Patterns

Pattern 1: One ref accumulates many notes

Pattern 2: One note connects many refs

Pattern 3: Planning graph

Check for notes

Leave notes

Target stability

Note format

Note history

Historical notes for a file

Slots

Setup (once per clone)

jj+git colocated repos

Files

Compare with similar skills

Similar skills

Finishing a Development Branch

Code Design Rationale Investigator

Contributor-First PR Merge

Migrate Internal Package into Ghost

Create Pull Request

Git Merge Conflict Resolver

Related

Questions about Mycelium