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.
npx skills add mhylle/claude-skills-collection --skill context-savergit clone --depth 1 https://github.com/mhylle/claude-skills-collectionWrote 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.
[](https://agentmods.dev/skills/mhylle/claude-skills-collection/context-saver)<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/context-saver"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/context-saver/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.
<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/context-saver"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/context-saver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00161 | $0.02086 |
| Opus 5 | $0.00081 | $0.01043 |
| Sonnet 5 | $0.00032 | $0.00417 |
| Haiku 4.5 | $0.00016 | $0.00209 |
Grade A, and why
context-saver 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 12d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Saver
Preserve in-flight session state to disk for seamless continuation in another session. Extracts signal from noise — captures the essential state (trajectory, decisions, active files, blockers, next steps) while discarding ephemeral details (exploratory reads, rejected paths, verbose tool output).
Scope — how this differs from auto-memory
Claude Code has a built-in memory system at ~/.claude/projects/.../memory/ that captures long-lived, typed entries (user, feedback, project, reference). That handles persistent knowledge: facts about you, validated preferences, project-state that's true across sessions.
This skill handles what memory doesn't: the snapshot of what you're actively doing right now. It's the answer to "I need to step away mid-task — capture where I am so a new session can pick up seamlessly."
- Memory: "This user prefers pytest over unittest." (always true, loads into every session)
- This skill: "Currently refactoring
src/auth/token.service.ts:45-78— tried approach A (failed, see line 60), now trying approach B, next step is to update the test at__tests__/token.service.spec.ts:120." (true right now, for this specific task)
Memory grows bigger over months; context-save docs are ephemeral — delete them once the work they describe lands.
When to Use
- User explicitly requests context saving ("save context", "checkpoint this")
- Before ending a long session with incomplete work
- When switching focus and needing to preserve state
- Before attempting risky operations that may require rollback
- When collaborating and need to hand off context to another session
Core Principles
Signal Extraction Priority
- Trajectory (highest): What is the user trying to achieve? What's the end goal?
- Decisions: What choices were made and why? What was rejected?
- State: What code is being modified? What's the current progress?
- Approaches: What has been tried? What worked/failed?
- Noise (discard): Exploratory reads, rejected paths, verbose tool output
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.
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.
- 12d ago First seen · 262 lines · 161 tokens per session scan A 9cde8e334732
context-saver is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 9d ago), licensed MIT. It adds 161 tokens to every session and 2,086 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.