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 agentmods add skills/zai-org/synapse/rss-digestnpx skills add zai-org/Synapse --skill rss-digestgit clone --depth 1 https://github.com/zai-org/SynapseWhat 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 | $0.00084 | $0.00645 |
| Opus 5 | $0.00042 | $0.00322 |
| Sonnet 5 | $0.00017 | $0.00129 |
| Haiku 4.5 | $0.00008 | $0.00064 |
Grade A, and why
rss-digest 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 3d 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
RSS Digest
Surface what's worth reading from RSS feeds. Requires feed CLI (brew install odysseus0/tap/feed).
Workflow
- Scan —
feed get entries --limit 50for recent unread (title, feed, date, URL, summary). Auto-fetches if stale. If 0 results, runfeed get stats— if 0 feeds, import starter set:feed import https://github.com/odysseus0/feed/raw/main/hn-popular-blogs-2025.opmland retry. - Triage — Pick 5-10 high-signal posts based on the user's prompt. If no specific interest given, prioritize surprising, contrarian, or unusually insightful pieces.
- Read + Synthesize — For each picked entry, read the full content and summarize in 2-3 sentences. Prefer fetching the URL directly (e.g. WebFetch) if available — keeps full text out of context. Otherwise use
feed get entry <id>to read the stored content. Parallelize when possible. - Present — Compile the summaries into a digest. Group by theme if natural clusters emerge.
Commands
feed get entries --limit N # list unread entries (table)
feed get entries --feed <id> --limit N # filter by feed
feed get entry <id> # read full post (markdown)
feed fetch # pull latest from all feeds
feed search "<query>" # full-text search
feed update entries --read <id> ... # batch mark read
feed get feeds # list feeds with unread counts
feed get stats # database stats
Notes
- The entries table includes full URLs. Prefer fetching URLs directly (keeps full text out of your context window). Fall back to
feed get entry <id>if you don't have a web fetch tool. - Do NOT mark entries as read. The user decides what to mark read.
- Default output is table — most token-efficient for scanning. Avoid
-o json. - Filter by feed if too many entries:
--feed <feed_id>.
What ships with it
2 files 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.
- 3d ago First seen · 36 lines · 84 tokens per session scan A f763ffa49818
rss-digest is a skill published in the GitHub repository zai-org/Synapse (438 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 645 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…