Skip to main content
skill CX Codex

recency-guard — Claude Code skill: what it does, how to install

recency-guard validates time-sensitive facts in assistant answers, cross-checking software releases, pricing, policy changes, and docs against live sources.

no license 203 installs ★ 3 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add b-mendoza/agent-skills --skill recency-guard -a claude-code
Open on GitHub

What recency-guard does

This skill serves as a read-only validation coordinator driven by a strict state machine. Before presenting an answer, it breaks down the prompt, drafts an internal claim ledger, and calls two dedicated helpers. The recency-checker inspects dates against live records, while claim-verifier stresses key statements for unsupported claims and counterexamples.

Instead of full rewrites, the workflow favors minimal safe adjustments. If evidence is thin, it qualifies or drops the statement. High-impact operations such as deploying code, executing purchases, or altering remote systems are out of scope; the skill solely reviews informational content.

Without working search, browsing, or documentation retrieval tools, the orchestrator refuses to rely on the language model's frozen weights for fresh facts and strips unverified time-sensitive claims.

What it helps with

  • verify current pricing tiers and package availability
  • confirm library release versions against official docs
  • catch exaggerated technical claims in draft answers
  • strip outdated claims when online verification tools fail

Example prompts for the agent

  • Compare the current React data-fetching libraries and verify their latest release status
  • Audit this draft response about cloud provider pricing tiers for stale details
  • Review the migration steps against the newest documentation release

How to install recency-guard

1Skills CLI (Vercel)

npx skills add b-mendoza/agent-skills --skill recency-guard -a claude-code

2Manually: put the files in place

~/.claude/skills/recency-guard/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/recency-guard/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about recency-guard

How to install recency-guard in Claude Code?

Run npx skills add b-mendoza/agent-skills --skill recency-guard -a claude-code in your terminal.

What does recency-guard do?

It intercepts drafts containing dates, rankings, or prices, routing them through specialized checking subagents to replace stale claims with verified details.

How does recency-guard handle missing search tools?

When search and documentation tools cannot be reached, the orchestrator marks tools unavailable and removes or qualifies time-sensitive lines instead of guessing from training data.

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set12

The whole set →
validate-implementation-plan validate-implementation-plan audits implementation plans for speculative complexity and brittle assumptions. Writes a separate audit file without touching the original plan. CX Codex +1 1,800installs pr-creator pr-creator turns your current branch into a pull or merge request. You see the exact preview first and approve before anything is created. CX Codex +1 195installs review-pull-request review-pull-request audits a single GitHub pull request across isolated stages, drafts a local Markdown report, and posts comments only when confirmed. CX Codex +1 161installs committing-scoped-changes committing-scoped-changes splits an explicit list of files or folders into separate git commits and leaves the rest of the working tree alone. CX Codex +1 153installs responding-to-pr-review-comments The responding-to-pr-review-comments skill gathers pull request comments, assesses the feedback, and drafts replies. With confirmation, it can post approved text to supported GitHub comment threads. CX Codex +1 144installs clarifying-assumptions clarifying-assumptions — a skill that runs the conversational layer for plan verification. Asks critical questions upfront or before individual tasks, delegates artifact analysis to subagents. CX Codex +1 129installs refactoring-code refactoring-code is a Claude Code skill that stages simplification refactors: approve the plan before edits, then check that behaviour stays the same. CX Codex +1 124installs diagnosing-root-causes The diagnosing-root-causes skill traces bugs, regressions, and CI/CD failures from supplied evidence, then produces a reviewed root-cause report. Use it when a problem report needs investigation rather than guesswork. CX Codex +1 122installs

Project sponsors

Companies that keep this analytics open