A skill for deciding which old saved snapshots to remove based on age, count, or storage size. It can protect the newest, pinned, or labelled snapshots.

Use it when changing cleanup rules, storage limits, retention previews, or the behavior that runs after a new snapshot is saved.

It prevents saved data from growing without limit while ensuring the newest snapshot and selected protected snapshots remain available.

How hoangsonww/Diffuse-Native-Apps configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to hoangsonww/Diffuse-Native-Apps. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/hoangsonww/Diffuse-Native-Apps/master/.agents/skills/retention/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/hoangsonww/Diffuse-Native-Apps

Made for: Claude Code, Codex.

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/hoangsonww/diffuse-native-apps/retention/github.svg)](https://agentmods.dev/skills/hoangsonww/diffuse-native-apps/retention)

Your own site

<a href="https://agentmods.dev/skills/hoangsonww/diffuse-native-apps/retention"><img src="https://agentmods.dev/badge/skills/hoangsonww/diffuse-native-apps/retention/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/hoangsonww/diffuse-native-apps/retention"><img src="https://agentmods.dev/badge/skills/hoangsonww/diffuse-native-apps/retention.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 203 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	$0.00036	$0.00203
Opus 5.5	$0.00014	$0.00081
Sonnet 5.5	$0.00007	$0.00041
Haiku 4.5	$0.00004	$0.00020

Measured yesterday against content hash 1dd32bce2c73, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

retention 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 yesterday.

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.

.agents/skills/retention/SKILL.md · 18 lines

What it actually says

Retention

RetentionPlanner.plan is pure over [SnapshotSummary]. Preview in UI must use the same function the store executes.

Newest snapshot is never deleted. Without it there is nothing to compare against.
Default policy: 90 days, 1 GiB, protects pinned and labelled snapshots.
Empty labels are not protection. protectsLabelled / protectsPinned can be turned off.
Protected snapshots do not consume the count/size quota.
Age is applied before count/size so the reason stays tooOld when both apply.
SnapshotService.capture runs retention after save so the new snapshot always survives a tight limit.

Tests: Tests/Domain/RetentionPlannerTests.swift and retention invariants.

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.

yesterday First seen · 18 lines · 36 tokens per session scan A 1dd32bce2c73

Subscribe to this mod's changes

retention is a skill published in the GitHub repository hoangsonww/Diffuse-Native-Apps (11 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 203 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-07.

android device-monitoring gradle ios ipados jetpack-compose

retention next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
retentionhoangsonww/Diffuse-Native-Apps	Skill	11	1mo ago	MIT	A	36	Claude Code, Codex
motion-design-prokelvinkosbab/AppBootstrapAI	Skill	8	yesterday	MIT	A	129	Claude Code
android-adaptive-layout-prokelvinkosbab/AppBootstrapAI	Skill	8	yesterday	MIT	A	147	Claude Code
android-gradle-architecture-prokelvinkosbab/AppBootstrapAI	Skill	8	yesterday	MIT	A	74	Claude Code
r8-shrink-prokelvinkosbab/AppBootstrapAI	Skill	8	yesterday	MIT	A	87	Claude Code
xml-to-compose-migration-prokelvinkosbab/AppBootstrapAI	Skill	8	yesterday	MIT	A	78	Claude Code
swift-adaptive-layout-prokelvinkosbab/AppBootstrapAI	Skill	8	yesterday	MIT	A	129	Claude Code

Diffuse-Native-Apps: Skill for Claude Code