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 Supa-Media/context --skill syncgit clone --depth 1 https://github.com/Supa-Media/contextWrote 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/supa-media/context/sync)<a href="https://agentmods.dev/skills/supa-media/context/sync"><img src="https://agentmods.dev/badge/skills/supa-media/context/sync/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/supa-media/context/sync"><img src="https://agentmods.dev/badge/skills/supa-media/context/sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00052 | $0.00499 |
| Opus 5.5 | $0.00021 | $0.00200 |
| Sonnet 5.5 | $0.00010 | $0.00100 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
sync 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.
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.
What it actually says
Sync what you know into Context
Use this the first time a person connects Context, and again whenever they connect another AI app: each app knows different things about them, and each run adds what this one knows to what is already there.
The user may name topics after the command (for example "work people"). By default cover their work and projects, the people they work with (names and roles only, never contact details), and how they like to work. Cover their personal life only if they ask for it.
Steps
- Call
orientfirst and follow the folders it reports. Their front page states their own conventions; follow those over anything here. - Go through everything you know about each topic, not a few highlights. Plan one short note per project, area, person or topic, and keep going until you have covered all of them.
- Before writing each one, search for a note that already covers it with
search, thenfetch.- Nothing covers it: create a note with
write. - A note covers it: add what it lacks with
write, passing theexpected_etagfromfetch. Remove nothing, so what another app wrote survives. - You disagree with it: add your version as "According to :" under what is there, rather than replacing it, and list it in the report.
- Nothing covers it: create a note with
- Say which folder each note goes in as you write it. Don't stop to ask the user before writing; they asked for this run.
- Only write what you actually know. Don't touch
index.mdorprivacy.md, and don't delete or move anything. - Finish with a note called "Sync report" in the inbox that lists what you added, what you updated, and any disagreements, one line each.
If no context MCP tools are available, tell the user to connect Context
first, for example by running npx -y @supa-media/context install.
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 Changed 5509d5025cc2
- 1mo ago First seen · 42 lines · 52 tokens per session scan A 3064830985cb
sync is a skill published in the GitHub repository Supa-Media/context (3 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 499 once invoked, about $0.0002 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 2026-09-27.
Other skills, from other repositories
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.
link-retrieve
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.
link-ingest
Use when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates through the CLI without MCP.
my-wiki
A skill for managing a local Markdown knowledge vault that stores captured webpages, PDFs, Office files, notes, images, folders, and ZIP files. It links preserved source material, called References, to durable topic pages, called Concepts.
vault-summarize
Use when the user asks to summarize, digest, or get an overview of a folder, project, or set of notes in their markdown vault — runs the vault's batched map-reduce recipe so note bodies stay out of the retained conversation context.