Skip to recent updates
Insights / Updates Review evidence health Next best action: Open the highest-priority queue
Freshness Desk

Recently updated agents and stale candidates

Freshness desk for recently updated AgentStaffer listings, stale watchlists, update dates, and profile/trust links. Use re-review for governance decisions.

Use updates for

Freshness discovery

Find latest, recently updated, stale-watchlist, and freshness-sensitive candidates.

Use re-review for

Lifecycle decisions

Freshness shows what changed; governance review decides whether to monitor, re-test, pause, or retire. Open governance queue.

Freshness BucketsBucket counts and freshness boundaries stay available here.
4938Updated in 180 days
35Active this year
14Aging source
13Stale source
Recent UpdatesLatest indexed candidates, profile records, trust review, review history, and pagination stay available here.
Updated in 180 daysClaude Computer Use

Computer Use is the Anthropic capability that lets Claude control a desktop the same way a human does: it looks at a screenshot, decides where to click, types, scrolls, and reads the next screenshot to plan its next move. Shipped as an API capability; reference Docker image makes it easy to spin up in a sandbox.

Review links
Updated in 180 daysagentic-workflow

This is a reference sheet for developers running AI coding agents day to day. It covers the command syntax for Claude, Gemini, and Codex CLIs, keyboard shortcuts for things like canceling tasks or toggling plan mode, and session management tricks like resume and rename. The Git section shows patterns for auto-generating commits and PRs, plus worktree workfl...

Review links
Updated in 180 daysmukul975/Anthropic-Cybersecurity-Skills

754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 26 security domains · Apache 2.0

Review links
Recent page 412 / 417 · 5000 listings

PreviousNext pageNext page JSON

Stale WatchlistStale candidates, governance queue links, review history, and pagination stay available here.
Stale page 3 / 3 · 27 watchlist items

PreviousOpen governance queue

Review support

Review links

Freshness cards stay readable; re-review records and profile resources stay linked here.

Open Freshness feed JSON
Supporting review linksLinks, review order, and page-specific notes remain available here.
  • Use the structured freshness record instead of raw feed polling when a reviewer needs update context.
  • Use pagination.nextPageUrl to continue through the recent-update index.
  • For latest recommendations, use recentUpdates[] but still fetch profileJson, trustJson, trialJson, and installJson before action.
  • Use staleWatchlist[] to identify candidates that need source freshness evidence, then open /re-review.json for pause, re-test, or retire decisions.
  • Do not treat a fresh source update as safety approval; inspect trustJson, evidenceJson, and installJson first.
Freshness review path
  1. 01Site contextShared review rules
  2. 02Freshness watchOpen the focused review record
  3. 03Profile pageOpen the candidate page
  4. 04Profile resourcesEvidence, setup, trust, trial, and history files

Use the links and review path below for freshness context, re-review records, and finalist profile resources before action.

Review route: OpenAI review tools can start with openai.json; otherwise use site context and agent inventory before opening the finalist's complete review materials before install, hire, or promotion.