What is context-save?

A skill for saving the lasting results of a coding-agent session into the user's Context notes. It covers decisions, constraints, preferences, fixes, open questions, and rules for updating or creating notes.

It is for responding to requests to remember work, updating existing notes safely, and recording session decisions and other durable information.

It keeps useful session knowledge from being lost and avoids adding duplicate notes.

context-save — Skill for Claude Code by Supa-Media/context

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 Supa-Media/context --skill context-save

Clone the repo

git clone --depth 1 https://github.com/Supa-Media/context

Made for: Claude Code.

Or install context, the plugin that ships this one along with the rest of its 5 skills, 1 MCP server.

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/supa-media/context/context-save/github.svg)](https://agentmods.dev/skills/supa-media/context/context-save)

Your own site

<a href="https://agentmods.dev/skills/supa-media/context/context-save"><img src="https://agentmods.dev/badge/skills/supa-media/context/context-save/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/supa-media/context/context-save"><img src="https://agentmods.dev/badge/skills/supa-media/context/context-save.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 250 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	$0.00250
Opus 5.5	$0.00014	$0.00100
Sonnet 5.5	$0.00007	$0.00050
Haiku 4.5	$0.00004	$0.00025

Measured 21d ago against content hash 9f6d1bffadc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

context-save 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 21d 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.

plugins/context/skills/context-save/SKILL.md · 22 lines

What it actually says

Save this session to Context

List the durable things this session produced: decisions and why, constraints, preferences, names, fixes, open questions. Skip anything transient.
For each one that belongs in an existing note, call search, then fetch, then write with the expected_etag you read. Improve that note; do not add a near-duplicate.
For anything that needs a new note, tell the user which folder it will land in and wait for their go before calling write.
Call write with action save_session and the session's decisions and, if the user wants it, the user-visible messages. Never include system prompts, internal reasoning, credentials or raw tool output.
Tell the user what was written and where, one line per note.

If no context MCP tools are available, tell the user to run npx -y @supa-media/context install.

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.

21d ago Changed 9f6d1bffadc5
1mo ago First seen · 22 lines · 36 tokens per session scan A 995556a3be0e

Subscribe to this mod's changes

context-save is a skill published in the GitHub repository Supa-Media/context (3 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 250 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 2026-09-26.

Memory and context cloudflare-workers convex knowledge-base markdown mcp model-context-protocol

context-save next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
context-saveSupa-Media/context	Skill	3	today	MIT	A	36	Claude Code
llm-wikizosmaai/pi-llm-wiki	Skill	626	4d ago	MIT	A	52	Claude Code
link-memorygowtham0992/link	Skill	218	9d ago	MIT	A	0	Claude Code, Codex
link-retrievegowtham0992/link	Skill	218	9d ago	MIT	A	42	Claude Code, Codex
link-ingestgowtham0992/link	Skill	218	9d ago	MIT	A	44	Claude Code, Codex
my-wikiNimaChu/my-wiki	Skill	127	24d ago	MIT	A	51	Codex
obsidian-vault-workflowaka-kika/kika-obsidian-mcp	Skill	17	yesterday	MIT	A	0	Claude Code, Codex