sdsrss/agentsmd/agentsmd-version-cascade

Claude Code and agent skill by sdsrss/agentsmd

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Scan README prose for stale same-major version tokens. Use before release or after a version bump. Not for structured package/plugin/spec version equality; read-only.

Install

npx vskill@latest install sdsrss/agentsmd/agentsmd-version-cascade

SKILL.md

agentsmd-version-cascade

Use the selected SKILL.md absolute path from the live skills list; never infer it from the process cwd. Define and call the adjacent launcher in the same shell. The launcher preserves selected bundle → manifest-owned standalone → versioned CLI identity checks and exports plugin context only for a verified selected bundle.

bash
SKILL_MD="<selected SKILL.md absolute path from the live skills list>"
agentsmd_skill_run() {
node "$(dirname "$SKILL_MD")/scripts/agentsmd-run.js" "$SKILL_MD" "$@"
}

drift.test.js gate #5 asserts the version matches across the 5 structured places (named JSON fields + the two CODEX-CODING-SPEC vX.Y.Z headers). It cannot see a version token embedded in narrative text. This scans the prose READMEs for a current-major token whose minor has drifted:

bash
agentsmd_skill_run
agentsmd_skill_run --json
  • Compares each vMAJOR.MINOR(.patch) token against hard-rules.json spec_version at minor granularity (patch-insensitive). The major-token regex is derived per run, so it keeps working after a major bump instead of going silently blind.
  • Intentional historical/example refs are allowlisted (INTENTIONAL_TOKENS in the script — the rename version, an example --ref tag). A genuinely new deliberate historical ref means a conscious addition there.
  • ok + exit 0 = no stale prose token; a stale/missing token → exit 1 with file:line — found … (expected …).

Read-only. From the repo instead of an install: node scripts/version-cascade-check.js. For the structured cross-file version check in a source checkout, run node scripts/tests/drift.test.js. Release and broad shared changes still require the full gate.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/sdsrss/agentsmd/agentsmd-version-cascade/badge)](https://verified-skill.com/skills/sdsrss/agentsmd/agentsmd-version-cascade)

Something wrong with this skill or its page? Tell us.