New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Encephalon

by isaachinman in isaachinman/encephalon

A skill your agent uses when working in a Git repository that has Encephalon installed, especially before making repository assumptions or when a durable decision, architecture change, convention…

MITAuto-check passedDevelopment

Install Encephalon

skills CLI
$ npx skills add isaachinman/encephalon --skill encephalon -a claude-code

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

GitHub CLI
$ gh skill install isaachinman/encephalon encephalon --agent claude-code

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

Manual copy
$ git clone --depth 1 https://github.com/isaachinman/encephalon.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/encephalon .claude/skills/encephalon && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

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

Facts

Skill name
encephalon
GitHub stars
137
Token cost
~1k tokens
SKILL.md length
427 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when working in a Git repository that has Encephalon installed, especially before making repository assumptions or when a durable decision, architecture change, convention…

  • Working in a Git repository that has Encephalon installed
  • SKILL.md covers Start with active knowledge, Decide whether to record, Preserve append-only history and Enrich an initial baseline, plus 1 more section
  • Calls npx
  • Especially before making repository assumptions

What it does

Encephalon is an agent skill from isaachinman/encephalon. Use when working in a Git repository that has Encephalon installed, especially before making repository assumptions or when a durable decision, architecture change, convention, incident, workflow, pull request, or material technical change may need long-term agent knowledge.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Pull requests. It works with Git. The repository describes itself as: Durable, repository-local memory for coding agents, stored as Git-mergeable JSON and indexed by SQLite for fast search. The licence is MIT.

When your agent uses it

  • Working in a Git repository that has Encephalon installed
  • Especially before making repository assumptions
  • A durable decision
  • Architecture change

Example prompts

  • “/encephalon”

Requirements

  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit c684705. 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

    Shell commands in SKILL.md call:

    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, 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

Encephalon loads about 1k tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 427 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from isaachinman/encephalon at commit c684705, republished under its MIT licence (© isaachinman). 427 words, ~1,026 tokens.

Download SKILL.mdSave it as .claude/skills/encephalon/SKILL.md (or your agent's skills folder).
name
encephalon
description
Use when working in a Git repository that has Encephalon installed, especially before making repository assumptions or when a durable decision, architecture change, convention, incident, workflow, pull request, or material technical change may need long-term agent knowledge.

Encephalon

Use Encephalon as the repository's durable, append-only memory. Query it before relying on assumptions; update it only when future agents would materially benefit.

Start with active knowledge

Before planning or changing unfamiliar repository behaviour, search for the relevant subject:

bash
npx --no-install encephalon search --compact "authentication deployment"
npx --no-install encephalon show --id "<relevant-id>" --active-only

Prefer compact search or one batched gather call before loading full records. Treat missing results as missing stored knowledge, not proof that a fact is false. Do not inspect or edit record JSON directly.

Search terms are literal and combined with AND. Payload-only matches can have a metadata/summary fallback snippet; use show to understand them. Reads prepare the disposable cache automatically. Recoverable corruption rebuilds once; a foreign cache or unsafe layout fails closed. Follow the reported recovery action rather than deleting cache or canonical files blindly. An add error with canonicalCommitted: true means the record already exists: inspect its ID and validate before retrying.

Decide whether to record

Record only durable, high-signal knowledge:

  • decisions and their rationale;
  • architecture, boundaries, and conventions;
  • repeatable development, release, or operational workflows;
  • incidents with lasting diagnosis or prevention guidance;
  • material technical or pull-request changes that reverse or invalidate prior knowledge;
  • stable repository context that cannot be cheaply rediscovered.

Do not record routine edits, status updates, chat or log dumps, temporary debugging state, speculative ideas, source-code summaries, generated output, secrets, credentials, personal data, or local absolute paths.

Show full SKILL.md (206 more words)Show less

Preserve append-only history

Search the intended subject first. If active knowledge changes, add a replacement that supersedes every active head for the same kind and subject; never rewrite or delete the earlier record.

bash
npx --no-install encephalon search --compact "api authentication strategy"
npx --no-install encephalon add \
  --kind decision \
  --subject api.authentication \
  --source agent \
  --supersedes "<active-id>" \
  --data '{"summary":"Use signed bearer tokens","rationale":["Supports non-browser clients"],"consequences":["Deploy token verification before clients"]}' \
  --text "authentication bearer token deployment"
npx --no-install encephalon validate

Use a recommended kind (decision, architecture, convention, workflow, incident, or context) when it fits. Keep subjects stable and payloads concise, structured, factual, and portable. Use --artifact only for an existing immutable supporting file beneath _artifacts/<kind>/<id>/; choose --id first when creating artifacts before their record.

Include new records and artifacts with the Git change that made them true. Do not stage, commit, push, or open a pull request automatically.

Enrich an initial baseline

After encephalon init, read the active generated baseline and inspect the repository semantically. Add only durable facts the safe scanner could not derive, such as architectural boundaries, non-obvious conventions, and the reasons behind essential workflows. Do not restate manifests, script keys, or filenames already captured by the generated records. Init does not traverse source directories or generate language counts or file totals; discover languages or frameworks separately when the task needs them.

Finish

Run:

bash
npx --no-install encephalon validate

Resolve validation failures before presenting the related change. Mention the added or superseded record IDs in the handoff so the user can review them with the code.

© isaachinman, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/encephalon of isaachinman/encephalon.

Open the folder on GitHubat commit c684705

Compare with similar skills

Encephalon 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.

Encephalon compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Encephalon this skillisaachinman/encephalon137—~1kAutomated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Open Code Review CLIalibaba/open-code-review46k—~3.1kAutomated safety check: PassApache-2.0
Create Pull Requestcline/cline70k1 repos~1.6kAutomated safety check: PassApache-2.0
Pull Request Title and Body Writeropeninterpreter/openinterpreter69k2 repos~1.1kAutomated safety check: PassApache-2.0

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.

    297k GitHub starsUsed in 5 repos~1.9k 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

  • Open Code Review CLI

    alibaba/open-code-review

    Runs the ocr command-line tool to review Git changes, a commit or a branch comparison with an AI model, returning line-level comments and optionally applying fixes.

    46k GitHub stars~3.1k tokensUpdated yesterday
    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

  • Pull Request Title and Body Writer

    openinterpreter/openinterpreter

    Rewrites the title and body of one or more pull requests with gh, leading with why the change was made, then what changed, and describing only the net result.

    69k GitHub starsUsed in 2 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    86k GitHub stars~1.4k tokensUpdated yesterday
    DevelopmentAuto-check passed

Works with

Categories

Questions about Encephalon

What does Encephalon do?

A skill your agent uses when working in a Git repository that has Encephalon installed, especially before making repository assumptions or when a durable decision, architecture change, convention…. Encephalon is an agent skill from isaachinman/encephalon. Use when working in a Git repository that has Encephalon installed, especially before making repository assumptions or when a durable decision, architecture change, convention, incident, workflow, pull request, or material technical change may need long-term agent knowledge.

When should I use Encephalon?

Encephalon fits situations like: working in a Git repository that has Encephalon installed; especially before making repository assumptions; A durable decision; architecture change.

How do I install Encephalon in Claude Code?

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

How do I install Encephalon in Codex?

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

Can I use Encephalon 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 isaachinman/encephalon --skill encephalon -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/encephalon, .gemini/skills/encephalon, .github/skills/encephalon and .opencode/skills/encephalon in your project.

What does Encephalon need to run?

Going by SKILL.md and its folder, Encephalon needs the command-line tools its instructions call (npx). Our summary lists: Node.js.

Does Encephalon access the network?

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

Is Encephalon 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. Review the folder before installing.

What licence does Encephalon use?

Encephalon is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Encephalon use?

About 1k tokens (SKILL.md is roughly 4.1k 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 Encephalon?

Skills that share tags, products or a category with Encephalon: Finishing a Development Branch (obra/superpowers, 297k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars), Open Code Review CLI (alibaba/open-code-review, 46k stars) and Create Pull Request (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Encephalon?

isaachinman (a GitHub user) maintains it in isaachinman/encephalon, which has 137 GitHub stars. The repository was last updated on October 10, 2026.

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