Agent skill

Context Decay

by pskoett in pskoett/pskoett-ai-skills

Revalidate persistent agent knowledge by classifying why it can become stale and how quickly it changes, then retain, revise, externalize, or retire it.

No licenceAuto-check passedAgent Workflows

Install Context Decay

skills CLI
$ npx skills add pskoett/pskoett-ai-skills --skill context-decay -a claude-code

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

GitHub CLI
$ gh skill install pskoett/pskoett-ai-skills context-decay --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/pskoett/pskoett-ai-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/context-decay .claude/skills/context-decay && 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-decay
GitHub stars
314
Token cost
~3.3k tokens
SKILL.md length
1,703 words
Files
82 (incl. references)
Skills in repo
24
Repo updated
First seen
Licence
None found

At a glance

Revalidate persistent agent knowledge by classifying why it can become stale and how quickly it changes, then retain, revise, externalize, or retire it.

  • Works in 5 steps: Identify the claim and its authority → Classify cause and cadence → Check and choose an outcome → …
  • Reviewing skills
  • SKILL.md covers Install, Scope and activation, 1. Identify the claim and its… and 2. Classify cause and cadence, plus 6 more sections
  • Runs Python scripts from its folder; calls gh and npx

What it does

Context Decay is an agent skill from pskoett/pskoett-ai-skills. Revalidate persistent agent knowledge by classifying why it can become stale and how quickly it changes, then retain, revise, externalize, or retire it. Use when reviewing skills, stored instructions, facts, preferences, assumptions, or workflows; when an owner, decision, or dependency changes; or when self-improvement captures, reviews, or promotes a learning. Works independently of self-improvement. Not for runtime context-window degradation, unsaved task observations, or age-based deletion.

Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 91 other files, including reference files (for example `evals/EVALS.md`, `evals/evals.json` and `evals/fixtures/approval-blocked-heal/.learnings/HEALS.md`).

It sits in Agent Workflows, covering Context engineering.

When your agent uses it

  • Reviewing skills
  • Stored instructions
  • Dependency changes
  • Self-improvement captures

Example prompts

  • “/context-decay”

Requirements

  • Python 3
  • Node.js

Workflow steps

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

  1. Identify the claim and its authority
  2. Classify cause and cadence
  3. Check and choose an outcome
  4. Keep a lightweight context contract
  5. Apply within scope and report

What it can do on your machine

Read from SKILL.md and the folder at commit 5a836dc. 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, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • gh
    • npx

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

  • Network

    No URLs in SKILL.md. Its commands use gh and 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

Context Decay loads about 3.3k tokens when it runs, and up to ~6k if it reads all its reference files. Until then it costs about 128 tokens; SKILL.md has 1,703 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~128
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,703 words (~3,292 tokens).

“Persistent context needs a theory of how it could stop being useful. Decay type determines how to revalidate. Decay rate determines when. Age alone proves neither that context is wrong nor that it should be removed. Truth and usefulness must…”

— opening of SKILL.md by pskoett
name
context-decay

Read the full SKILL.md on GitHub

Files

SKILL.md and 81 other files (references) in skills/context-decay of pskoett/pskoett-ai-skills.

  • SKILL.md
  • evals/EVALS.md
  • evals/evals.json
  • evals/fixtures/approval-blocked-heal/.learnings/HEALS.md
  • evals/fixtures/approval-blocked-heal/failure.txt
  • evals/fixtures/approval-blocked-heal/installed/export-data/SKILL.md
  • evals/fixtures/approval-blocked-heal/skills/export-data/SKILL.md
  • evals/fixtures/approval-blocked-heal/skills/export-data/scripts/export.py
  • evals/fixtures/approval-blocked-heal/source-map.md
  • evals/fixtures/approval-blocked-heal/tool-docs.md
  • evals/fixtures/approved-skill-edit/installed
  • … and 71 more

Open the folder on GitHubat commit 5a836dc

Compare with similar skills

Context Decay 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 Decay compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Context Decay this skillpskoett/pskoett-ai-skills314—~3.3kAutomated safety check: PassNone
Context Mode Output Sandboxmksglu/context-mode26k—~4.1kAutomated safety check: PassCustom licence
Memori Long-Term MemoryMemoriLabs/Memori17k—~2kAutomated safety check: NotesCustom licence
Picoclaw Skill Creatorsipeed/picoclaw30k—~4.4kAutomated safety check: PassMIT
ccc Semantic Code Searchcocoindex-io/cocoindex-code2.8k—~938Automated safety check: PassApache-2.0
Context Mode for Antigravity CLImksglu/context-mode26k—~850Automated safety check: PassCustom licence

Similar skills

  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Memori Long-Term Memory

    MemoriLabs/Memori

    Connects Claude Code to Memori Cloud for long-term memory, recalling stored context before substantive replies and saving new context afterward.

    17k GitHub stars~2k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check: notes
  • Picoclaw Skill Creator

    sipeed/picoclaw

    Guidance for creating, updating and reviewing Picoclaw skills, from the SKILL.md structure to organizing bundled scripts, references and assets.

    30k GitHub stars~4.4k tokensUpdated 15 days ago
    Agent WorkflowsAuto-check passed
  • ccc Semantic Code Search

    cocoindex-io/cocoindex-code

    Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path.

    2.8k GitHub stars~938 tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • Routing rules for using context-mode MCP tools in Antigravity CLI: sandboxed code runs, file analysis, indexed search and web fetches that keep large output out of the conversation.

    26k GitHub stars~850 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Token Optimizer

    alexgreensh/token-optimizer

    Audit a Claude Code or Codex setup for context-window waste, then fix it and measure the savings.

    2.5k GitHub stars~3.6k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from pskoett/pskoett-ai-skills

All 24 skills in this repo
  • Self Improvement

    pskoett/pskoett-ai-skills

    Captures learnings, errors, corrections, and feature requests to enable continuous improvement.

    314 GitHub stars~5k tokensUpdated 4 days ago
    Auto-check passed
  • Self Improvement

    pskoett/pskoett-ai-skills

    Captures learnings, errors, corrections, and feature requests to enable continuous improvement.

    314 GitHub stars~5.4k tokensUpdated 4 days ago
    Auto-check passed
  • Self Healing

    pskoett/pskoett-ai-skills

    Active runtime recovery for coding agents: when something breaks mid-task, diagnose the root cause, write a fix, VERIFY by re-running the broken thing, then file a HEAL- entry to .learnings/HEALS.md…

    314 GitHub stars~5.3k tokensUpdated 4 days ago
    Auto-check: notes
  • Skill Tester

    pskoett/pskoett-ai-skills

    Validates all interactive skills in this repo against the Agent Skills spec, project conventions, and structural requirements.

    314 GitHub stars~1.3k tokensUpdated 4 days ago
    Auto-check passed
  • Skill Tester CI

    pskoett/pskoett-ai-skills

    Validates all CI skills in this repo. An agent skill from pskoett/pskoett-ai-skills.

    314 GitHub stars~845 tokensUpdated 4 days ago
    Auto-check passed
  • Eval Creator CI

    pskoett/pskoett-ai-skills

    [Beta] CI-only eval regression runner using gh-aw (GitHub Agentic Workflows).

    314 GitHub stars~2.2k tokensUpdated 4 days ago
    Auto-check passed

Categories

Questions about Context Decay

What does Context Decay do?

Revalidate persistent agent knowledge by classifying why it can become stale and how quickly it changes, then retain, revise, externalize, or retire it. Context Decay is an agent skill from pskoett/pskoett-ai-skills. Revalidate persistent agent knowledge by classifying why it can become stale and how quickly it changes, then retain, revise, externalize, or retire it.

When should I use Context Decay?

Context Decay fits situations like: reviewing skills; stored instructions; dependency changes; self-improvement captures.

How do I install Context Decay in Claude Code?

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

How do I install Context Decay in Codex?

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

Can I use Context Decay 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 pskoett/pskoett-ai-skills --skill context-decay -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-decay, .gemini/skills/context-decay, .github/skills/context-decay and .opencode/skills/context-decay in your project.

What does Context Decay need to run?

Going by SKILL.md and its folder, Context Decay needs Python for the scripts in its folder and the command-line tools its instructions call (gh and npx). Our summary lists: Python 3; Node.js.

Does Context Decay access the network?

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

Is Context Decay 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 Decay use?

No licence was found for Context Decay or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Context Decay use?

About 3.3k tokens (SKILL.md is roughly 13k 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 2.7k tokens, read only when the agent opens those files.

What are the alternatives to Context Decay?

Skills that share tags, products or a category with Context Decay: Context Mode Output Sandbox (mksglu/context-mode, 26k stars), Memori Long-Term Memory (MemoriLabs/Memori, 17k stars), Picoclaw Skill Creator (sipeed/picoclaw, 30k stars) and ccc Semantic Code Search (cocoindex-io/cocoindex-code, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Context Decay?

pskoett (a GitHub user) maintains it in pskoett/pskoett-ai-skills, which has 314 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 5, 2026.

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