This skill should be used when the user asks about "garbage collection rules", "entropy fighting", "documentation staleness", "dead code detection", "convention drift", "periodic checks", "auto-fix…

Custom licenceAuto-check passed

Install Garbage Collection

skills CLI
$ npx skills add Habitat-Thinking/ai-literacy-superpowers --skill garbage-collection -a claude-code

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

GitHub CLI
$ gh skill install Habitat-Thinking/ai-literacy-superpowers garbage-collection --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/Habitat-Thinking/ai-literacy-superpowers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ai-literacy-superpowers/skills/garbage-collection .claude/skills/garbage-collection && 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
garbage-collection
GitHub stars
114
Token cost
~2.2k tokens
SKILL.md length
1,099 words
Files
2 (incl. references)
Skills in repo
42
Repo updated
First seen
Licence
Custom licence

At a glance

This skill should be used when the user asks about "garbage collection rules", "entropy fighting", "documentation staleness", "dead code detection", "convention drift", "periodic checks", "auto-fix…

  • Works in 6 steps: Identify the entropy: what drifts over… → Describe the check: what would a… → Choose frequency: how fast does this… → …
  • Asks about garbage collection rules
  • SKILL.md covers Anatomy of a GC Rule, Choosing Frequency, The Auto-Fix Decision and Common GC Categories, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Garbage Collection is an agent skill from Habitat-Thinking/ai-literacy-superpowers. This skill should be used when the user asks about "garbage collection rules", "entropy fighting", "documentation staleness", "dead code detection", "convention drift", "periodic checks", "auto-fix rules", or needs guidance on the Garbage Collection section of HARNESS.md.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/gc-catalogue.md`).

The repository describes itself as: A set of Claude Code and GitHub Copilot plugins providing the AI Literacy framework's complete development workflow — harness engineering, agent orchestration, literate….

When your agent uses it

  • Asks about garbage collection rules
  • Entropy fighting
  • Documentation staleness
  • Dead code detection

Example prompts

  • “garbage collection rules”
  • “entropy fighting”
  • “documentation staleness”
  • “/garbage-collection”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Identify the entropy: what drifts over time in this codebase?
  2. Describe the check: what would a reviewer look for?
  3. Choose frequency: how fast does this entropy accumulate?
  4. Decide enforcement: can a deterministic tool check this, or does it
  5. Apply the auto-fix rubric: is automated correction safe?
  6. Add the rule to HARNESS.md's Garbage Collection section

What it can do on your machine

Read from SKILL.md and the folder at commit 9d35995. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Garbage Collection loads about 2.2k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 73 tokens; SKILL.md has 1,099 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~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); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,099 words (~2,202 tokens).

“Garbage collection in a harness context means periodic checks that fight entropy — the slow drift that neither real-time hooks nor PR gates catch. Documentation goes stale, conventions erode, dead code accumulates, dependencies fall behind.”

— opening of SKILL.md by Habitat-Thinking, Custom licence
name
garbage-collection

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (references) in ai-literacy-superpowers/skills/garbage-collection of Habitat-Thinking/ai-literacy-superpowers.

  • SKILL.md
  • references/gc-catalogue.md

Open the folder on GitHubat commit 9d35995

Compare with similar skills

Garbage Collection 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.

Garbage Collection compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Garbage Collection this skillHabitat-Thinking/ai-literacy-superpowers114—~2.2kAutomated safety check: PassCustom licence
Config Gcaffaan-m/ECC276k1 repos~2kAutomated safety check: PassMIT
Alfworld Object Disposerzjunlp/SkillNet1.4k—~341Automated safety check: PassMIT
Alfworld Receptacle Searcherzjunlp/SkillNet1.4k—~709Automated safety check: PassMIT
Jev Blocksautonomous-ai/openharness1.2k—~1kAutomated safety check: PassMIT
Harness Gck1ein-chen/Harness-Starter119—~360Automated safety check: PassMIT

Similar skills

  • Config Gc

    affaan-m/ECC

    Garbage collection for your Claude Code configuration. An agent skill from affaan-m/ECC.

    276k GitHub starsUsed in 1 repo~2k tokens
    Agent WorkflowsAuto-check passed
  • This skill disposes of an object by placing it into a disposal receptacle like a garbage can.

    1.4k GitHub stars~341 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • This skill searches for a specific receptacle (e.g., garbage can, cabinet) by systematically exploring the environment, checking multiple locations until found.

    1.4k GitHub stars~709 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Jev Blocks

    autonomous-ai/openharness

    Design a falling-blocks challenge for Jev in blocks.json (gravity, speedup, garbage, a custom board, the piece mix, the style line), then read the verdict and report where Jev starts to break.

    1.2k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Harness Gc

    k1ein-chen/Harness-Starter

    Garbage Collection Agent — 定期扫描项目健康状态,检测文档/代码一致性漂移,自动发起修复提案。

    119 GitHub stars~360 tokensUpdated 15 days ago
    Auto-check passed
  • Debug Bo Corruption

    Xilinx/mlir-air

    A skill your agent uses when an NPU kernel passes its standalone shape test but produces NaN, garbage, or stale values when invoked as part of a larger pipeline.

    150 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

More from Habitat-Thinking/ai-literacy-superpowers

All 42 skills in this repo
  • Advocatus Diaboli

    Habitat-Thinking/ai-literacy-superpowers

    A skill your agent uses when acting as the adversarial spec reviewer — raises steel-manned objections across six categories before plan approval, requires evidence per objection, and discloses what…

    114 GitHub stars~4.2k tokensUpdated 18 days ago
    Auto-check passed
  • AI Literacy Assessment

    Habitat-Thinking/ai-literacy-superpowers

    This skill should be used when the user asks to "assess AI literacy", "run an assessment", "check literacy level", "evaluate our AI collaboration", "where are we on the framework", or wants to…

    114 GitHub stars~3.7k tokensUpdated 18 days ago
    Auto-check passed
  • Carpaccio

    Habitat-Thinking/ai-literacy-superpowers

    A skill your agent uses when acting as the cadence governor — slices a raw task description into thin, end-to-end-complete pieces before any spec is written; produces a structured slicing record for…

    114 GitHub stars~1.8k tokensUpdated 18 days ago
    Auto-check passed
  • Choice Cartographer

    Habitat-Thinking/ai-literacy-superpowers

    A skill your agent uses when acting as the decision-archaeology agent — surfaces decisions a spec has made (including the silent ones), emits each material choice as a Henney-style pattern story for…

    114 GitHub stars~4.1k tokensUpdated 18 days ago
    Auto-check passed
  • Constraint Design

    Habitat-Thinking/ai-literacy-superpowers

    This skill should be used when the user asks to "add a constraint", "design a constraint", "write a harness rule", "choose enforcement type", "promote a constraint", "configure a verification slot"…

    114 GitHub stars~1.8k tokensUpdated 18 days ago
    Auto-check passed
  • Cost Tracking

    Habitat-Thinking/ai-literacy-superpowers

    A skill your agent uses when the user wants to capture AI tool costs, review spending trends, set cost budgets, or integrate cost data into health snapshots — guides quarterly cost capture, records…

    114 GitHub stars~1.7k tokensUpdated 18 days ago
    Auto-check passed

Questions about Garbage Collection

What does Garbage Collection do?

This skill should be used when the user asks about "garbage collection rules", "entropy fighting", "documentation staleness", "dead code detection", "convention drift", "periodic checks", "auto-fix…. Garbage Collection is an agent skill from Habitat-Thinking/ai-literacy-superpowers.md.

When should I use Garbage Collection?

Garbage Collection fits situations like: asks about garbage collection rules; entropy fighting; documentation staleness; dead code detection.

How do I install Garbage Collection in Claude Code?

Run `npx skills add Habitat-Thinking/ai-literacy-superpowers --skill garbage-collection -a claude-code`. Or copy the skill folder (ai-literacy-superpowers/skills/garbage-collection in Habitat-Thinking/ai-literacy-superpowers) into .claude/skills/garbage-collection in your project. Claude Code loads it when a task matches its description.

How do I install Garbage Collection in Codex?

Run `npx skills add Habitat-Thinking/ai-literacy-superpowers --skill garbage-collection -a codex`. Or copy the skill folder (ai-literacy-superpowers/skills/garbage-collection in Habitat-Thinking/ai-literacy-superpowers) into .agents/skills/garbage-collection in your project. Codex loads it when a task matches its description.

Can I use Garbage Collection 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 Habitat-Thinking/ai-literacy-superpowers --skill garbage-collection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/garbage-collection, .gemini/skills/garbage-collection, .github/skills/garbage-collection and .opencode/skills/garbage-collection in your project.

What does Garbage Collection need to run?

SKILL.md names no scripts, command-line tools or credentials: Garbage Collection is instructions for the agent only.

Does Garbage Collection 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 Garbage Collection 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 Garbage Collection use?

Garbage Collection has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Garbage Collection use?

About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.8k tokens, read only when the agent opens those files.

What are the alternatives to Garbage Collection?

Skills that share tags, products or a category with Garbage Collection: Config Gc (affaan-m/ECC, 276k stars), Alfworld Object Disposer (zjunlp/SkillNet, 1.4k stars), Alfworld Receptacle Searcher (zjunlp/SkillNet, 1.4k stars) and Jev Blocks (autonomous-ai/openharness, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Garbage Collection?

Habitat-Thinking (a GitHub organization) maintains it in Habitat-Thinking/ai-literacy-superpowers, which has 114 GitHub stars. The repository holds 42 skills in this directory. The repository was last updated on September 20, 2026.

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