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

Context Loader

by DeL-TaiseiOzaki in DeL-TaiseiOzaki/claude-code-orchestra

ALWAYS activate this skill at the start of every task. An agent skill from DeL-TaiseiOzaki/claude-code-orchestra.

MITAuto-check passed

Install Context Loader

skills CLI
$ npx skills add DeL-TaiseiOzaki/claude-code-orchestra --skill context-loader -a claude-code

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

GitHub CLI
$ gh skill install DeL-TaiseiOzaki/claude-code-orchestra context-loader --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/DeL-TaiseiOzaki/claude-code-orchestra.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/context-loader .claude/skills/context-loader && 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
context-loader
GitHub stars
199
Token cost
~1.3k tokens
SKILL.md length
688 words
Files
2
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

ALWAYS activate this skill at the start of every task. An agent skill from DeL-TaiseiOzaki/claude-code-orchestra.

  • Works in 4 steps: Resolve the Read Plan → Read Everything in read_order, Then… → Route the Task Before Touching It → …
  • SKILL.md covers Purpose, When to Activate, Workflow and Key Rules, plus 1 more section
  • Runs Python scripts from its folder; calls python3

What it does

Context Loader is an agent skill from DeL-TaiseiOzaki/claude-code-orchestra. ALWAYS activate this skill at the start of every task. Load shared rules from .claude/rules/ and project design context before executing any task.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `load_context.py`).

The licence is MIT.

Example prompts

  • “Use the context-loader skill to alway activate this skill at the start of every task. An agent skill from DeL-TaiseiOzaki/claude-code-orchestra”
  • “/context-loader”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Resolve the Read Plan
  2. Read Everything in read_order, Then Surface Gaps
  3. Route the Task Before Touching It
  4. Execute or Delegate the Task

What it can do on your machine

Read from SKILL.md and the folder at commit ef0d8f8. 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 script files (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

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

  • Network

    No URLs in SKILL.md.

    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

Context Loader loads about 1.3k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 688 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 DeL-TaiseiOzaki/claude-code-orchestra at commit ef0d8f8, republished under its MIT licence (© DeL-TaiseiOzaki). 688 words, ~1,301 tokens.

Download SKILL.mdSave it as .claude/skills/context-loader/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
context-loader
description
ALWAYS activate this skill at the start of every task. Load shared rules from .claude/rules/ and project design context before executing any task.

Context Loader Skill

Purpose

Load canonical shared context from .claude/ plus project-owned design documentation so every agent runtime uses the same source files.

When to Activate

ALWAYS - This skill must run at the beginning of every task to load project context.

Workflow

Step 1: Resolve the Read Plan

Run load_context.py to get a deterministic read order instead of a hand-maintained file list, so the plan never drifts from what actually exists on disk:

bash
python3 .claude/skills/context-loader/load_context.py [--task-libraries name,name]

Pass --task-libraries (comma-separated) when the task names specific libraries; the script matches them against .claude/docs/libraries/ and folds any hits into the read order.

The JSON reports {ok, read_order, rules, state, design, progress, libraries, missing, unreadable, warnings}. read_order is the exact ordered list of repo-relative paths to read, in this order:

  1. the rule files in .claude/rules/ (coding principles, delegation, dev environment, language, security, testing, tiers, CLI execution, Codex delegation, and any newly added rule file);
  2. .claude/STATE.md — the active main agent and current working blocks;
  3. PROGRESS.md — the rolling record of the latest five checkpoints, and the session-to-session continuity /feature reads first;
  4. .claude/docs/DESIGN.md — architecture decisions and constraints;
  5. any matched library docs.
Step 2: Read Everything in read_order, Then Surface Gaps

Read each path in read_order. Then check the rest of the report:

  • missing — canonical files that do not exist at all (e.g. .claude/docs/DESIGN.md, PROGRESS.md). Report these; do not silently proceed as if they were empty.
  • unreadable — files that do exist but could not be read or decoded. This is a filesystem or encoding problem, not an un-bootstrapped repository: do not respond by suggesting /init.
  • warnings — design.placeholder is tri-state: true means .claude/docs/DESIGN.md is absent or still the uninitialised /init template (its "Background & Purpose" section is empty), false means real prose, and null means the marker heading is gone so the question cannot be answered. progress.entries: 0 means PROGRESS.md exists but holds no checkpoint entry.
  • libraries.matched vs libraries.files — matched is what read_order included for the current task; files is every doc that exists. If a library relevant to the task isn't in files at all, its documentation simply doesn't exist yet.

Exit code 2 means .claude/rules/ or .claude/STATE.md is missing entirely or unreadable — treat this as a hard stop, not a warning.

Show full SKILL.md (323 more words)Show less
Step 3: Route the Task Before Touching It

.claude/rules/delegation.md was just loaded, and it applies from here on: the default is to delegate, and working alone is the exception. Before the first Read, Grep, or Edit of the actual task, decide the route out loud:

  1. Does the whole task fall on the Self-Handle List (answer from loaded context · one known file, ~20 lines or fewer · a named gate or a skill-bundled lead script · user interaction)? If yes, do it directly.
  2. Otherwise name the route from the rule's table — general-purpose-sonnet, general-purpose-opus, codex-debugger, Codex, fable-advisor — or the skill that owns the workflow, and delegate with all six elements of the Subagent Prompt Contract.
  3. Split independent units and launch them in one message so they run in parallel.

Deciding the route after investigating is the anti-pattern the rule names: the investigation was itself the delegable work. When both routes look defensible, delegate.

Step 4: Execute or Delegate the Task

With the loaded context, execute the route chosen in Step 3, following:

  • Coding principles from rules
  • Design decisions from DESIGN.md
  • Library constraints from docs

If the work was delegated, verification stays here: run the acceptance checks and inspect the diff before reporting the result as done.

Key Rules

The rules themselves live in the files read_order enumerates — restating them here would be a hand-maintained duplicate of authoritative content, which is the drift this script exists to prevent. Apply what you read in .claude/rules/coding-principles.md, dev-environment.md, language.md, security.md, and testing.md.

Output

After loading context, briefly confirm to the user per .claude/rules/language.md:

  • how many rule files were read, and that .claude/STATE.md was read;
  • the missing, unreadable, and warnings arrays quoted verbatim from the JSON — not paraphrased, not summarised as "no issues";
  • design.placeholder and progress.entries as reported;
  • the route chosen in Step 3 — the subagent, Codex, or skill that will do the work, or, when handling it directly, which Self-Handle List item applies;
  • ready to execute the task.

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

Files

SKILL.md and 1 other file in .claude/skills/context-loader of DeL-TaiseiOzaki/claude-code-orchestra.

  • SKILL.md
  • load_context.py

Open the folder on GitHubat commit ef0d8f8

Compare with similar skills

Context Loader 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.

Context Loader compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Context Loader this skillDeL-TaiseiOzaki/claude-code-orchestra199—~1.3kAutomated safety check: PassMIT
Modeling Activation MetricsPostHog/posthog40k—~1.4kAutomated safety check: PassCustom licence
Summarize Activityalpinejs/alpine32k—~1.6kAutomated safety check: NotesMIT
Duplicate Id Activethedaviddias/Front-End-Checklist74k—~440Automated safety check: PassMIT
Puzzle Activity Plannersickn33/agentic-awesome-skills47k1 repos~790Automated safety check: PassMIT
Adding Activity LoggingPostHog/posthog40k—~1.5kAutomated safety check: PassCustom licence

Similar skills

  • Modeling Activation Metrics

    PostHog/posthog

    Official

    Build reusable activation models — an activation-rate metric and a per-user/per-account activated flag — on either PostHog data-warehouse views (HogQL) or an external dbt project.

    40k GitHub stars~1.4k tokensUpdated today
    Data & AnalyticsAuto-check passed

  • Summarize Activity

    alpinejs/alpine

    Summarize recent GitHub activity — discussions, PRs, issues, events, traffic — into an actionable report so you can stay on top of the project without reading everything.

    32k GitHub stars~1.6k tokensUpdated 5 days ago
    Backend & APIsAuto-check: notes

  • Duplicate Id Active

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Use unique IDs for active elements.

    74k GitHub stars~440 tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed

  • Puzzle Activity Planner

    sickn33/agentic-awesome-skills

    Plan puzzle-based activities for classrooms, parties, and events with pre-configured generator links

    47k GitHub starsUsed in 1 repo~790 tokens
    Auto-check passed

  • Adding Activity Logging

    PostHog/posthog

    Official

    Adds or changes activity logging (the audit trail) for a Django model in PostHog.

    40k GitHub stars~1.5k tokensUpdated today
    Backend & APIsAuto-check passed

  • Containing Active Breach

    mukul975/Anthropic-Cybersecurity-Skills

    Executes containment strategies to stop active adversary operations and prevent lateral movement during a confirmed security breach.

    34k GitHub stars~2.7k tokensUpdated 1 mo ago
    SecurityAuto-check passed

More from DeL-TaiseiOzaki/claude-code-orchestra

All 15 skills in this repo

  • Codex System

    DeL-TaiseiOzaki/claude-code-orchestra

    Codex CLI handles planning, design, and complex code implementation.

    199 GitHub stars~4.2k tokensUpdated 20 days ago
    Auto-check passed

  • Design Tracker

    DeL-TaiseiOzaki/claude-code-orchestra

    Record a project design decision into .claude/docs/DESIGN.md through the shared typed writer.

    199 GitHub stars~2k tokensUpdated 20 days ago
    Auto-check passed

  • Feature

    DeL-TaiseiOzaki/claude-code-orchestra

    Unified feature planning & implementation skill — replaces the old /add-feature and /start-feature skills (both trigger phrases still apply here).

    199 GitHub stars~9.4k tokensUpdated 20 days ago
    Auto-check passed

  • Plan

    DeL-TaiseiOzaki/claude-code-orchestra

    Create a detailed implementation plan for a feature or task.

    199 GitHub stars~2.1k tokensUpdated 20 days ago
    Auto-check passed

  • Catchup

    DeL-TaiseiOzaki/claude-code-orchestra

    Comprehensive onboarding for new or returning contributors. An agent skill from DeL-TaiseiOzaki/claude-code-orchestra.

    199 GitHub stars~1.8k tokensUpdated 20 days ago
    Auto-check passed

  • Checkpointing

    DeL-TaiseiOzaki/claude-code-orchestra

    Save session activity, rebuild rolling PROGRESS.md, and compact stale working blocks in .claude/STATE.md.

    199 GitHub stars~1.8k tokensUpdated 20 days ago
    Auto-check passed

Questions about Context Loader

What does Context Loader do?

ALWAYS activate this skill at the start of every task. An agent skill from DeL-TaiseiOzaki/claude-code-orchestra. Context Loader is an agent skill from DeL-TaiseiOzaki/claude-code-orchestra. ALWAYS activate this skill at the start of every task.

How do I install Context Loader in Claude Code?

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

How do I install Context Loader in Codex?

Run `npx skills add DeL-TaiseiOzaki/claude-code-orchestra --skill context-loader -a codex`. Or copy the skill folder (.claude/skills/context-loader in DeL-TaiseiOzaki/claude-code-orchestra) into .agents/skills/context-loader in your project. Codex loads it when a task matches its description.

Can I use Context Loader 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 DeL-TaiseiOzaki/claude-code-orchestra --skill context-loader -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/context-loader, .gemini/skills/context-loader, .github/skills/context-loader and .opencode/skills/context-loader in your project.

What does Context Loader need to run?

Going by SKILL.md and its folder, Context Loader needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Context Loader access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Context Loader 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 Context Loader use?

Context Loader 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 Context Loader use?

About 1.3k tokens (SKILL.md is roughly 5.2k 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 Context Loader?

Skills that share tags, products or a category with Context Loader: Modeling Activation Metrics (PostHog/posthog, 40k stars), Summarize Activity (alpinejs/alpine, 32k stars), Duplicate Id Active (thedaviddias/Front-End-Checklist, 74k stars) and Puzzle Activity Planner (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Context Loader?

DeL-TaiseiOzaki (a GitHub user) maintains it in DeL-TaiseiOzaki/claude-code-orchestra, which has 199 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on September 20, 2026.

Source: DeL-TaiseiOzaki/claude-code-orchestra on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.