A tool for finding old decision and reasoning notes whose conditions may no longer be true. An invalidation trigger is the event that makes a past conclusion outdated.

Use it to scan a vault of project notes, rank possibly stale entries, and ask which ones should be marked superseded.

It helps separate current guidance from decisions that may have been superseded by newer code, notes, or time.

decay — Skill for Claude Code by Aiyo28

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Aiyo28/memento-os --skill memento-decay

Clone the repo

git clone --depth 1 https://github.com/Aiyo28/memento-os

Made for: Claude Code.

Or install memento-os, the plugin that ships this one along with the rest of its 7 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aiyo28/memento-os/memento-decay/github.svg)](https://agentmods.dev/skills/aiyo28/memento-os/memento-decay)

Your own site

<a href="https://agentmods.dev/skills/aiyo28/memento-os/memento-decay"><img src="https://agentmods.dev/badge/skills/aiyo28/memento-os/memento-decay/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aiyo28/memento-os/memento-decay"><img src="https://agentmods.dev/badge/skills/aiyo28/memento-os/memento-decay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 564 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00089	$0.00564
Opus 5	$0.00044	$0.00282
Sonnet 5	$0.00018	$0.00113
Haiku 4.5	$0.00009	$0.00056

Measured 11d ago against content hash 39c19acac937, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

decay scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (decay.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

adapters/codex/skills/memento-decay/SKILL.md · 52 lines

What it actually says

/decay

Walk every [D] artifact past its freshness window, look for evidence the invalidation trigger has fired, prompt the user to mark stale ones superseded.

Signals

Signal	Weight	Source
Git commits matching N invalidator keywords	+1 (1kw) / +3 (2kw) / +5 (3+kw), cap +6	`git log --grep` grouped per-commit
Newer vault artifact with ≥2 overlapping terms	+3 per match	scan all `_context.md`
Age past 90 days with no other signal	+1	weak

Tiers: score ≥3 = LIKELY STALE; 1–2 = REVIEW; 0 = skipped unless --all.

How to invoke

python3 .agents/skills/decay/decay.py [VAULT_ROOT] \
  [--age 30] [--format text|json] [--no-git] [--all] [--stopwords <file>]

Vault root resolution: argument → $MEMENTO_VAULT_ROOT → CWD.

A per-vault stopword list at <vault_root>/.memento-stopwords is loaded automatically (one word per line, # comments). Use this to suppress project-specific noise words (e.g., the project's own name, dominant tech terms).

Agent flow

Run with --format json.
For each LIKELY STALE candidate, prompt: "Mark [D]#N as superseded? (y/n/skip)".
On y: change priority cell to superseded. Update Decisions/ file frontmatter if present.
On n: optionally capture an [I] insight explaining why the trigger hasn't fired.

Don't

Don't auto-supersede. Every supersession needs user confirmation.
Don't pass --no-git silently when a repo IS available.
Don't widen the vault-overlap threshold (≥2 keywords).

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

decay.py 14 KB runs code

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago First seen · 52 lines · 89 tokens per session scan A 39c19acac937

Subscribe to this mod's changes

decay is a skill published in the GitHub repository Aiyo28/memento-os (4 stars, last pushed 5d ago), licensed MIT. It adds 89 tokens to every session and 564 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Memory and context Research agent-memory agent-skills ai-memory claude-code-plugin codex

tree-ring-memory

Guides AI agents in using Tree Ring Memory for durable recall, project decisions, user preferences, warnings, future seeds, privacy-safe memory capture, and lifecycle-aware forgetting.

TerminallyLazy/tree-ring-memory-claude-plugin · 38 tokens

memory-to-skill

Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…

zilliztech/memsearch · 82 tokens

plur-create-engrams

Create or improve PLUR engrams from conversations, documents, decisions, observations, and explicit preferences. Use for memory extraction, engram authoring, or reviewing proposed memories, including global, scoped, pinned, retrieved, and provisional knowledge. Ordinary use of existing memories does not require this…

plur-ai/plur · 66 tokens

recall

Recall this repository's OwnMem local memory before changing code, and keep it healthy. Use when a repository contains .ownmem/, when past debugging lessons could apply ("have we hit this before", "why is it done this way"), or when the user mentions ownmem, project memory, or recalling across sessions.

grpcer/ownmem · 66 tokens

init

Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.

grpcer/ownmem · 43 tokens

Effective Memory

The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.

plur-ai/plur · 44 tokens