Agent skill

Artifact Type Tailored Context

by closedloop-ai in closedloop-ai/claude-plugins

Compresses artifacts for judge evaluation. An agent skill from closedloop-ai/claude-plugins.

Apache-2.0Auto-check: notesWriting & Content

Install Artifact Type Tailored Context

skills CLI

$ npx skills add closedloop-ai/claude-plugins --skill artifact-type-tailored-context -a claude-code

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

GitHub CLI

$ gh skill install closedloop-ai/claude-plugins artifact-type-tailored-context --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/closedloop-ai/claude-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/judges/skills/artifact-type-tailored-context .claude/skills/artifact-type-tailored-context && 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/

Paste into Claude Code

Install the "artifact-type-tailored-context" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/judges/skills/artifact-type-tailored-context into .claude/skills/artifact-type-tailored-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "artifact-type-tailored-context", 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.

$skill-installer

$skill-installer install https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/judges/skills/artifact-type-tailored-context

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add closedloop-ai/claude-plugins --skill artifact-type-tailored-context -a codex

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

GitHub CLI

$ gh skill install closedloop-ai/claude-plugins artifact-type-tailored-context --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/judges/skills/artifact-type-tailored-context .agents/skills/artifact-type-tailored-context && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

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

Paste into Codex

Install the "artifact-type-tailored-context" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/judges/skills/artifact-type-tailored-context into .agents/skills/artifact-type-tailored-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "artifact-type-tailored-context", 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 closedloop-ai/claude-plugins --skill artifact-type-tailored-context -a cursor

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

GitHub CLI

$ gh skill install closedloop-ai/claude-plugins artifact-type-tailored-context --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/judges/skills/artifact-type-tailored-context .cursor/skills/artifact-type-tailored-context && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

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

Paste into Cursor

Install the "artifact-type-tailored-context" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/judges/skills/artifact-type-tailored-context into .cursor/skills/artifact-type-tailored-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "artifact-type-tailored-context", 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.

gemini skills install

$ gemini skills install https://github.com/closedloop-ai/claude-plugins.git --path plugins/judges/skills/artifact-type-tailored-context

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add closedloop-ai/claude-plugins --skill artifact-type-tailored-context -a gemini-cli

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

GitHub CLI

$ gh skill install closedloop-ai/claude-plugins artifact-type-tailored-context --agent gemini-cli

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

Manual copy

$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/judges/skills/artifact-type-tailored-context .gemini/skills/artifact-type-tailored-context && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

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

Paste into Gemini CLI

Install the "artifact-type-tailored-context" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/judges/skills/artifact-type-tailored-context into .gemini/skills/artifact-type-tailored-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "artifact-type-tailored-context", 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 closedloop-ai/claude-plugins artifact-type-tailored-context

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 closedloop-ai/claude-plugins --skill artifact-type-tailored-context -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/judges/skills/artifact-type-tailored-context .github/skills/artifact-type-tailored-context && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

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

Paste into GitHub Copilot

Install the "artifact-type-tailored-context" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/judges/skills/artifact-type-tailored-context into .github/skills/artifact-type-tailored-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "artifact-type-tailored-context", 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 closedloop-ai/claude-plugins --skill artifact-type-tailored-context -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 closedloop-ai/claude-plugins artifact-type-tailored-context --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/judges/skills/artifact-type-tailored-context .opencode/skills/artifact-type-tailored-context && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

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

Paste into OpenCode

Install the "artifact-type-tailored-context" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/judges/skills/artifact-type-tailored-context into .opencode/skills/artifact-type-tailored-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "artifact-type-tailored-context", 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: artifact-type-tailored-context
GitHub stars: 122
Token cost: ~2.1k tokens
SKILL.md length: 777 words
Files: 6
Skills in repo: 43
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Compresses artifacts for judge evaluation. An agent skill from closedloop-ai/claude-plugins.

Works in 4 steps: Read Artifact → Count Raw Tokens → Apply Tiered Summarization Strategy → …
Tasks that involve Summarization
SKILL.md covers Purpose, Task Context, Input Parameters and Execution Workflow, plus 3 more sections
Calls uv

What it does

Artifact Type Tailored Context is an agent skill from closedloop-ai/claude-plugins. Compresses artifacts for judge evaluation. Reads a single raw artifact, applies tiered summarization within a token budget, and returns compacted content with metadata. Isolation via forked context prevents pollution of agent context

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files (for example `preambles/code_preamble.md`, `preambles/common_input_preamble.md` and `preambles/feature_preamble.md`).

It sits in Writing & Content, covering Summarization, LLM cost and token optimization and Codebase knowledge for agents. The repository describes itself as: Open-source Claude Code plugins for multi-agent software delivery. Plan-first SDLC workflow, code review, LLM quality judges, and self-learning — grounded in your codebase… The licence is Apache-2.0.

When your agent uses it

Tasks that involve Summarization
Tasks that involve LLM cost and token optimization
Tasks that involve Codebase knowledge for agents

Example prompts

“Use the artifact-type-tailored-context skill to compress artifacts for judge evaluation. An agent skill from closedloop-ai/claude-plugins”
“/artifact-type-tailored-context”

Requirements

Pre-approved tools (allowed-tools): Read, Bash

Workflow steps

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

Read Artifact
Count Raw Tokens
Apply Tiered Summarization Strategy
Return JSON Response

What it can do on your machine

Read from SKILL.md and the folder at commit 0e20ac0. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
- Read
- Bash
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, 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

Artifact Type Tailored Context loads about 2.1k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 777 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: ~2.1k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
```
allowed-tools: Read, Bash
```

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 closedloop-ai/claude-plugins at commit 0e20ac0, republished under its Apache-2.0 licence (© closedloop-ai). 777 words, ~2,104 tokens.

Download SKILL.mdSave it as .claude/skills/artifact-type-tailored-context/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.

name: artifact-type-tailored-context
description: Compresses artifacts for judge evaluation. Reads a single raw artifact, applies tiered summarization within a token budget, and returns compacted content with metadata. Isolation via forked context prevents pollution of agent context
allowed-tools: Read, Bash
context: fork
model: haiku

Artifact-Type-Tailored Context Skill

Purpose

Compress individual artifacts within a specified token budget using tiered summarization strategies. This skill operates in isolated forked context to prevent polluting the parent agent's context with large raw artifacts.

Task Context

You are responsible for compressing a single artifact file to fit within a token budget. Your responsibilities:

Read the raw artifact from the specified path
Count its tokens using the count_tokens.py script
Apply appropriate tiered summarization strategy
Return structured JSON with metadata

Success criteria:

Compressed content fits within token budget (or is properly truncated)
Valid JSON response with all required fields
Metadata accurately reflects truncation status

Input Parameters

You receive three required parameters:

Parameter	Type	Description
`artifact_path`	string	Path to artifact file relative to `$CLOSEDLOOP_WORKDIR`
`task_description`	string	Compression guidance (e.g., "preserve function signatures")
`token_budget`	integer	Maximum allowed tokens for compressed output

Execution Workflow

Step 1: Read Artifact

Read the artifact from its absolute path:

bash

# Construct full path
ARTIFACT_FULL_PATH="$CLOSEDLOOP_WORKDIR/$artifact_path"

Use the Read tool to load the artifact content. If the file does not exist, skip to error handling.

Step 2: Count Raw Tokens

Invoke the count_tokens.py script to get accurate token count:

bash

cd "$CLOSEDLOOP_WORKDIR" && uv run count_tokens.py "$artifact_path"

Expected output format:

json

{
  "input_tokens": 1234
}

Parse the JSON output and extract input_tokens as raw_tokens.

Error handling:

If count_tokens.py fails (exit code non-zero), fallback to character-based heuristic: raw_tokens = len(content) / 4
Add warning to content preamble: [WARNING: Token count estimated via heuristic due to count_tokens.py failure]\n\n

Step 3: Apply Tiered Summarization Strategy

Choose strategy based on raw token count relative to budget:

Tier 1: Full Content (raw_tokens <= budget)

Condition: raw_tokens <= token_budget

Action: Return artifact unchanged

Metadata:

compacted_tokens = raw_tokens
truncated = false

No further processing needed.

Tier 2: Intelligent Compression (budget < raw_tokens <= budget * 1.5)

Condition: token_budget < raw_tokens <= token_budget * 1.5

Action: Apply artifact-type-specific compression preserving structure

Compression strategies by artifact type:

Artifact Type	Strategy
Code diffs	Keep function signatures, class declarations, and error messages. Summarize method bodies with `// ... (implementation omitted for brevity)`. Remove comments and blank lines.
JSON files	Keep all keys and structure. For arrays longer than 10 items, keep first 5 and last 2, replace middle with `{"_truncated": "N items omitted"}`. Truncate string values over 200 chars.
Log files	Keep all ERROR and WARNING lines. Summarize consecutive INFO lines with `... (N info lines omitted)`. Keep first and last 10 lines intact.
Plan/PRD markdown	Keep all headings, tables, and code blocks. Summarize paragraph text preserving key nouns and action verbs. Remove redundant examples.

Validation:

After compression, count tokens again:

bash

cd "$CLOSEDLOOP_WORKDIR" && uv run count_tokens.py <(echo "$compressed_content")

Decision tree:

If compacted_tokens <= token_budget: Success → Return with truncated = false
If compacted_tokens > token_budget: Compression failed → Fallback to Tier 3

Tier 3: Hard Truncation (raw_tokens > budget * 1.5 OR Tier 2 failed)

Condition: raw_tokens > token_budget * 1.5 OR compression in Tier 2 exceeded budget

Action: Hard truncate at character boundary

Algorithm:

Estimate truncation point: char_limit = token_budget * 4 (heuristic: 4 chars per token)
Find last paragraph boundary (double newline \n\n) before char_limit
Truncate at that boundary
Calculate truncated token count: truncated_tokens = raw_tokens - token_budget
Append truncation marker:

[TRUNCATED: content exceeds budget, remaining {truncated_tokens} tokens omitted]

Metadata:

compacted_tokens = token_budget (approximate)
truncated = true

Show full SKILL.md (284 more words)Show less

Step 4: Return JSON Response

Return structured JSON with strict schema:

json

{
  "artifact_name": "path/to/artifact.ext",
  "raw_tokens": 5000,
  "compacted_tokens": 2000,
  "truncated": false,
  "content": "compressed artifact content here..."
}

Field descriptions:

Field	Type	Description
`artifact_name`	string	Original artifact_path parameter
`raw_tokens`	integer	Token count from count_tokens.py on raw artifact
`compacted_tokens`	integer	Token count after compression (from count_tokens.py validation or estimate for Tier 1/3)
`truncated`	boolean	`true` if Tier 3 truncation applied, `false` otherwise
`content`	string	Compressed or truncated artifact content

Error Handling

Artifact Not Found

Condition: artifact_path does not exist at $CLOSEDLOOP_WORKDIR/<artifact_path>

Response:

json

{
  "artifact_name": "path/to/missing.ext",
  "raw_tokens": 0,
  "compacted_tokens": 0,
  "truncated": true,
  "content": "[ERROR: artifact not found at $CLOSEDLOOP_WORKDIR/path/to/missing.ext]"
}

count_tokens.py Failure

Condition: Script exits with non-zero code or returns invalid JSON

Action:

Fallback to character-based heuristic: raw_tokens = len(content) / 4
Prepend warning to content:

[WARNING: Token count estimated via heuristic due to count_tokens.py failure]

<original content follows>

Proceed with tiered strategy using estimated token count
Set truncated = false unless Tier 3 is applied

Invalid Compression Output

Condition: Tier 2 compression produces malformed content (e.g., invalid JSON syntax for JSON artifacts)

Action: Immediately fallback to Tier 3 hard truncation with truncated = true

Example Scenarios

Example 1: Small Artifact (Tier 1)

Input:

artifact_path: plan.json
token_budget: 5000
Raw tokens: 3200

Output:

json

{
  "artifact_name": "plan.json",
  "raw_tokens": 3200,
  "compacted_tokens": 3200,
  "truncated": false,
  "content": "<full plan.json content>"
}

Example 2: Medium Artifact (Tier 2)

Input:

artifact_path: git_diff
token_budget: 10000
Raw tokens: 12000 (1.2x budget)

Compression applied: Remove comments, summarize method bodies, keep signatures

Output:

json

{
  "artifact_name": "git_diff",
  "raw_tokens": 12000,
  "compacted_tokens": 9500,
  "truncated": false,
  "content": "<compressed diff with function signatures preserved>"
}

Example 3: Large Artifact (Tier 3)

Input:

artifact_path: outcomes.log
token_budget: 3000
Raw tokens: 25000 (8.3x budget)

Action: Hard truncate at ~12000 chars (3000 tokens * 4)

Output:

json

{
  "artifact_name": "outcomes.log",
  "raw_tokens": 25000,
  "compacted_tokens": 3000,
  "truncated": true,
  "content": "<first ~2900 tokens of log>\n\n[TRUNCATED: content exceeds budget, remaining 22000 tokens omitted]"
}

Notes

Context isolation: This skill runs in forked context. The raw artifact content does not pollute the parent agent's context.
Token counting accuracy: Always prefer count_tokens.py output over estimates. Only fallback to heuristics on failure.
Compression quality: Tier 2 strategies prioritize structural information (function signatures, keys) over verbose content (comments, redundant text).
Budget enforcement: Tier 3 truncation is a hard stop. Judges must lower confidence when evaluating truncated artifacts.

Files

SKILL.md and 5 other files in plugins/judges/skills/artifact-type-tailored-context of closedloop-ai/claude-plugins.

SKILL.md
preambles/code_preamble.md
preambles/common_input_preamble.md
preambles/feature_preamble.md
preambles/plan_preamble.md
preambles/prd_preamble.md

Open the folder on GitHubat commit 0e20ac0

Compare with similar skills

Artifact Type Tailored Context 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.

Artifact Type Tailored Context compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Artifact Type Tailored Context this skillclosedloop-ai/claude-plugins	122	—	~2.1k	Automated safety check: Notes	Apache-2.0	today
Context Compressionguanyang/open-agent-hub	973	2 repos	~4.6k	Automated safety check: Pass	MIT	today
Codememory Summarization Skillharrylettering/CodeMemory	158	—	~788	Automated safety check: Pass	None	2 days ago
News Aggregator Skillcclank/news-aggregator-skill	1.3k	—	~2.1k	Automated safety check: Pass	None	4 mo ago
Vss Search ArchiveNVIDIA-AI-Blueprints/video-search-and-summarization	1.9k	—	~3.6k	Automated safety check: Pass	Apache-2.0	today
Entroly Context Controljuyterman1000/entroly	472	—	~501	Automated safety check: Pass	Apache-2.0	today

Similar skills

Context Compression
guanyang/open-agent-hub
This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve…
973 GitHub starsUsed in 2 repos~4.6k tokens
AI & LLM EngineeringAuto-check passed
Codememory Summarization Skill
harrylettering/CodeMemory
This skill should be used when creating conversation summaries for CodeMemory, discussing summarization quality, optimizing DAG structure, or working with the compaction system.
158 GitHub stars~788 tokensUpdated 2 days ago
Writing & ContentAuto-check passed
News Aggregator Skill
cclank/news-aggregator-skill
Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 44+ sources including Hacker News, Lobsters, Dev.to, GitHub, arXiv, Hugging Face Papers, AIHOT, TLDR…
1.3k GitHub stars~2.1k tokensUpdated 4 mo ago
Writing & ContentAuto-check passed
Vss Search Archive
NVIDIA-AI-Blueprints/video-search-and-summarization
A skill your agent uses when a user wants to search archived VSS video or ingest or delete a source for search.
1.9k GitHub stars~3.6k tokensUpdated today
Writing & ContentAuto-check passed
Entroly Context Control
juyterman1000/entroly
Surgically select, compress, and recover codebase context using Entroly's MCP tools.
472 GitHub stars~501 tokensUpdated today
Agent WorkflowsAuto-check passed
Deepgram JS Text Intelligence
deepgram/deepgram-js-sdk
A skill your agent uses when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Text Intelligence / Read (/v1/read) for sentiment, summarization, topic detection, and intent…
276 GitHub stars~1.1k tokensUpdated 5 days ago
Writing & ContentAuto-check passed

More from closedloop-ai/claude-plugins

All 43 skills in this repo

Codex Review
closedloop-ai/claude-plugins
Run Codex to review a plan file and return structured feedback with a verdict.
122 GitHub stars~1.4k tokensUpdated today
Auto-check: notes
Critic Cache
closedloop-ai/claude-plugins
Check if critic reviews are still valid before re-running Phase 2.5 critics.
122 GitHub stars~528 tokensUpdated today
Auto-check: notes
Cross Repo Cache
closedloop-ai/claude-plugins
Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches.
122 GitHub stars~683 tokensUpdated today
Auto-check: notes
Eval Cache
closedloop-ai/claude-plugins
Check for a cached plan-evaluation.json result before launching the plan-evaluator agent.
122 GitHub stars~516 tokensUpdated today
Auto-check: notes
Find Plugin File
closedloop-ai/claude-plugins
This skill should be used when needing to locate files within the Claude Code plugins cache directory (~/.claude/plugins/cache).
122 GitHub stars~812 tokensUpdated today
Auto-check passed
Gh Monitor PR
closedloop-ai/claude-plugins
Start a detached GitHub pull-request monitor that wakes the exact launching Codex Desktop or CLI root through the managed Codex App Server when review, CI, conflict, merge-queue, closure, readiness…
122 GitHub stars~5.1k tokensUpdated today
Auto-check passed

Questions about Artifact Type Tailored Context

What does Artifact Type Tailored Context do?

Compresses artifacts for judge evaluation. An agent skill from closedloop-ai/claude-plugins. Artifact Type Tailored Context is an agent skill from closedloop-ai/claude-plugins. Compresses artifacts for judge evaluation.

When should I use Artifact Type Tailored Context?

Artifact Type Tailored Context fits situations like: tasks that involve Summarization; tasks that involve LLM cost and token optimization; tasks that involve Codebase knowledge for agents.

How do I install Artifact Type Tailored Context in Claude Code?

Run `npx skills add closedloop-ai/claude-plugins --skill artifact-type-tailored-context -a claude-code`. Or copy the skill folder (plugins/judges/skills/artifact-type-tailored-context in closedloop-ai/claude-plugins) into .claude/skills/artifact-type-tailored-context in your project. Claude Code loads it when a task matches its description.

How do I install Artifact Type Tailored Context in Codex?

Run `npx skills add closedloop-ai/claude-plugins --skill artifact-type-tailored-context -a codex`. Or copy the skill folder (plugins/judges/skills/artifact-type-tailored-context in closedloop-ai/claude-plugins) into .agents/skills/artifact-type-tailored-context in your project. Codex loads it when a task matches its description.

Can I use Artifact Type Tailored Context 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 closedloop-ai/claude-plugins --skill artifact-type-tailored-context -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/artifact-type-tailored-context, .gemini/skills/artifact-type-tailored-context, .github/skills/artifact-type-tailored-context and .opencode/skills/artifact-type-tailored-context in your project.

What does Artifact Type Tailored Context need to run?

Going by SKILL.md and its folder, Artifact Type Tailored Context needs the command-line tools its instructions call (uv). Its frontmatter pre-approves these tools: Read, Bash.

Does Artifact Type Tailored Context access the network?

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

Is Artifact Type Tailored Context safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Artifact Type Tailored Context use?

Artifact Type Tailored Context is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Artifact Type Tailored Context use?

About 2.1k tokens (SKILL.md is roughly 8.4k 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 Artifact Type Tailored Context?

Skills that share tags, products or a category with Artifact Type Tailored Context: Context Compression (guanyang/open-agent-hub, 973 stars), Codememory Summarization Skill (harrylettering/CodeMemory, 158 stars), News Aggregator Skill (cclank/news-aggregator-skill, 1.3k stars) and Vss Search Archive (NVIDIA-AI-Blueprints/video-search-and-summarization, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Artifact Type Tailored Context?

closedloop-ai (a GitHub organization) maintains it in closedloop-ai/claude-plugins, which has 122 GitHub stars. The repository holds 43 skills in this directory. The repository was last updated on October 7, 2026.

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

Install Artifact Type Tailored Context

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Artifact-Type-Tailored Context Skill

Purpose

Task Context

Input Parameters

Execution Workflow

Step 1: Read Artifact

Step 2: Count Raw Tokens

Step 3: Apply Tiered Summarization Strategy

Tier 1: Full Content (raw_tokens <= budget)

Tier 2: Intelligent Compression (budget < raw_tokens <= budget * 1.5)

Tier 3: Hard Truncation (raw_tokens > budget * 1.5 OR Tier 2 failed)

Step 4: Return JSON Response

Error Handling

Artifact Not Found

count_tokens.py Failure

Invalid Compression Output

Example Scenarios

Example 1: Small Artifact (Tier 1)

Example 2: Medium Artifact (Tier 2)

Example 3: Large Artifact (Tier 3)

Notes

Files

Compare with similar skills

Similar skills

More from closedloop-ai/claude-plugins

Related

Questions about Artifact Type Tailored Context