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/anthropics/knowledge-work-plugins/digestnpx skills add anthropics/knowledge-work-plugins --skill digestgit clone --depth 1 https://github.com/anthropics/knowledge-work-pluginsWhat 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 | $0.00048 | $0.01287 |
| Opus 5 | $0.00024 | $0.00643 |
| Sonnet 5 | $0.00010 | $0.00257 |
| Haiku 4.5 | $0.00005 | $0.00129 |
Grade A, and why
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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- digest — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Digest Command
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Scan recent activity across all connected sources and generate a structured digest highlighting what matters.
Instructions
1. Parse Flags
Determine the time window from the user's input:
--daily— Last 24 hours (default if no flag specified)--weekly— Last 7 days
The user may also specify a custom range:
--since yesterday--since Monday--since 2025-01-20
2. Check Available Sources
Identify which MCP sources are connected (same approach as the search command):
- ~~chat — channels, DMs, mentions
- ~~email — inbox, sent, threads
- ~~cloud storage — recently modified docs shared with user
- ~~project tracker — tasks assigned, completed, commented on
- ~~CRM — opportunity updates, account activity
- ~~knowledge base — recently updated wiki pages
If no sources are connected, guide the user:
To generate a digest, you'll need at least one source connected.
Check your MCP settings to add ~~chat, ~~email, ~~cloud storage, or other tools.
3. Gather Activity from Each Source
~~chat:
- Search for messages mentioning the user (
to:me) - Check channels the user is in for recent activity
- Look for threads the user participated in
- Identify new messages in key channels
~~email:
- Search recent inbox messages
- Identify threads with new replies
- Flag emails with action items or questions directed at the user
~~cloud storage:
- Find documents recently modified or shared with the user
- Note new comments on docs the user owns or collaborates on
~~project tracker:
- Tasks assigned to the user (new or updated)
- Tasks completed by others that the user follows
- Comments on tasks the user is involved with
~~CRM:
- Opportunity stage changes
- New activities logged on accounts the user owns
- Updated contacts or accounts
~~knowledge base:
- Recently updated documents in relevant collections
- New documents created in watched areas
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.
- 2d ago First seen · 174 lines · 48 tokens per session scan A d711d49b898e
digest is a skill published in the GitHub repository anthropics/knowledge-work-plugins (23,791 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 1,287 once invoked, about $0.0002 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…