Agent Plugins Marketplace
← All plugins

agentsmd

v5.4.3

CODEX-CODING-SPEC — global Codex workflow and evidence guidance, with native hooks for selected safety/report checks and rule-specific opportunity telemetry.

Codex17 Skills

By agentsmdLicense: MIT0 GitHub starsUpdated 2 weeks ago

Directory evidence

Runtimes
Codex
Parsed components
17 skill or MCP entries
Source updated
Sep 10, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install agentsmd for Codex

Installs for the current user
codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add agentsmd@agent-plugin-marketplace

Paste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/sdsrss/agentsmd

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

agentsmd/
├── .codex-plugin/plugin.json
├── skills/agentsmd-analyze/SKILL.md
├── skills/agentsmd-audit/SKILL.md
├── skills/agentsmd-design/SKILL.md
├── skills/agentsmd-doctor/SKILL.md
├── skills/agentsmd-init/SKILL.md
├── skills/agentsmd-lesson-bypass-audit/SKILL.md
├── skills/agentsmd-lint-argv/SKILL.md
├── skills/agentsmd-perf-baseline/SKILL.md
├── skills/agentsmd-restore/SKILL.md
├── skills/agentsmd-rules/SKILL.md
├── skills/agentsmd-safety-coverage-audit/SKILL.md
├── skills/agentsmd-sampling-audit/SKILL.md
├── skills/agentsmd-scorecard/SKILL.md
├── skills/agentsmd-sparkline/SKILL.md
├── skills/agentsmd-status/SKILL.md
├── skills/agentsmd-verify/SKILL.md
└── skills/agentsmd-version-cascade/SKILL.md

Included Skills17

agentsmd-analyzeskills/agentsmd-analyze/SKILL.md

Distill coding conventions from source into AGENTS.md (提炼代码约定). Use for naming/import/error-handling analysis after agentsmd-init. Not for stack detection or design tokens.

agentsmd-auditskills/agentsmd-audit/SKILL.md

Aggregate agentsmd rule-hit telemetry by section (遥测命中统计). Use for enforcement activity and raw hit counts. Not for promotion/demotion decisions or transcript violation rates; read-only.

agentsmd-designskills/agentsmd-design/SKILL.md

Extract CSS :root and Tailwind v4 @theme tokens into DESIGN.md plus an AGENTS.md pointer. Use for frontend design-system facts. Not for coding conventions, non-frontend repos, or Tailwind v3 config themes.

agentsmd-doctorskills/agentsmd-doctor/SKILL.md

Diagnose an agentsmd installation (安装故障诊断): prerequisites, hook registration/executability, config flags, and spec drift. Use after install/update or when hooks fail. Not for telemetry analysis; read-only.

agentsmd-initskills/agentsmd-init/SKILL.md

Generate or refresh project AGENTS.md stack facts, commands, and structure (生成项目指令). Use before convention analysis. Not for inferring coding conventions or design tokens.

agentsmd-lesson-bypass-auditskills/agentsmd-lesson-bypass-audit/SKILL.md

Measure whether surfaced memory hints were later cited in Codex transcripts. Use for memory hint follow-through and bypass rates. Not for rule-hit governance or memory editing; read-only.

agentsmd-lint-argvskills/agentsmd-lint-argv/SKILL.md

Detect silent-fallback argv parsing in agentsmd bin/ and scripts/. Use when adding or reviewing a CLI flag/parser. Not for runtime hook command parsing or general linting; static read-only gate.

agentsmd-perf-baselineskills/agentsmd-perf-baseline/SKILL.md

Benchmark native hook wall-clock cost with OFF/ON medians in an isolated CODEX_HOME. Use for latency or disablement decisions. Not for correctness, install health, or live telemetry.

agentsmd-restoreskills/agentsmd-restore/SKILL.md

Restore hooks.json, config.toml, and AGENTS.md from an agentsmd pre-install snapshot. Use after a bad install/update merge. Not for ordinary uninstall; dry-run unless confirmed.

agentsmd-rulesskills/agentsmd-rules/SKILL.md

Review agentsmd rule promotion/demotion signals (规则升降级治理) using manifest and eligible telemetry. Use to govern the always-on spec. Not for raw hit listings or automatic spec edits; read-only.

agentsmd-safety-coverage-auditskills/agentsmd-safety-coverage-audit/SKILL.md

Check hook claims, bypass tokens, emitters, and hard-rules wiring for static drift. Use when reviewing safety hook metadata. Not for semantic security proof or runtime correctness.

agentsmd-sampling-auditskills/agentsmd-sampling-audit/SKILL.md

Retrospectively measure §10 vocabulary and report-order violations across assistant turns. Use for per-turn compliance rates. Not for live hook hits or spec editing; read-only.

agentsmd-scorecardskills/agentsmd-scorecard/SKILL.md

Aggregate the unified agentsmd quality scorecard (统一质量记分卡) with health, compatibility, conformance, performance, and measurement limits. Use for operator review or capture comparison. Not for automatic rule changes, release gates, or telemetry editing.

agentsmd-sparklineskills/agentsmd-sparkline/SKILL.md

Show multi-window trends in agentsmd rule activity and detect sections that went silent. Use for regressions or CHANGELOG trend tables. Not for single-window governance; read-only.

agentsmd-statusskills/agentsmd-status/SKILL.md

Show agentsmd install state (安装状态清单), registered hooks, preserved tenants, config flags, and telemetry rows. Use for a quick inventory. Not for health diagnosis or rule analysis.

agentsmd-verifyskills/agentsmd-verify/SKILL.md

Select and run change-aware validation (变更感知验证) with deterministic reasons and full-gate widening. Use for changed-file test planning or execution. Not for external canaries, release, deploy, or authorization.

agentsmd-version-cascadeskills/agentsmd-version-cascade/SKILL.md

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.

Plugin manifests1

.codex-plugin/plugin.json
{
  "name": "agentsmd",
  "version": "5.4.3",
  "surfaceProtocolVersion": 1,
  "description": "CODEX-CODING-SPEC — global Codex workflow and evidence guidance, with native hooks for selected safety/report checks and rule-specific opportunity telemetry.",
  "author": {
    "name": "agentsmd"
  },
  "license": "MIT",
  "keywords": [
    "coding-spec",
    "discipline",
    "hooks",
    "safety",
    "evidence",
    "code-quality",
    "governance",
    "workflow"
  ],
  "skills": "./skills/",
  "hooks": "./hooks.json",
  "interface": {
    "displayName": "agentsmd",
    "shortDescription": "A coding-discipline spec with bounded native checks and opportunity telemetry",
    "longDescription": "agentsmd combines a global SPINE/evidence spec with bounded native hooks. Hooks block selected dangerous shell, secret-commit, vocabulary, and known-red CI patterns; Stop observers report detectable structure issues. Telemetry records rule-specific opportunities and outcomes for operator review. Manifest-backed ownership keeps standalone lifecycle changes scoped to agentsmd artifacts.",
    "developerName": "agentsmd",
    "category": "Coding",
    "defaultPrompt": [
      "Review this coding task against the repository's AGENTS.md instructions and report evidence-backed findings."
    ],
    "capabilities": [
      "Read",
      "Write"
    ]
  }
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[agentsmd on Agent Plugins Marketplace](https://pluginsmp.com/plugins/agentsmd)