Home / vasilyu1983 / ai-agents-public · frameworks/shared-skills/AGENTS.md · GitHub

AGENTS.md@frameworks/shared-skills agentsA

AGENTS.md@frameworks/shared-skills is agent-read markdown (agents) from vasilyu1983/ai-agents-public.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Shared Skills Instructions

These rules apply under `frameworks/shared-skills/`. Root repository boundaries still apply.

## Change Contract

- Treat `graph/` (`graph.json`, `codex-discovery.md`, DOT, and per-router Mermaid) as the canonical catalog.
- After any `SKILL.md` body or routing change, run `python3 scripts/graph-export.py` from this directory. The graph hashes full skill bodies, so prose edits can make it stale. Stage the regenerated artifacts with the skill change; later body edits require regeneration again.
- When a `SKILL.md` exceeds 250 lines, add or retain a pilot task in `evals/tasks/pilot-router-and-long-skills.json` in the same change. Check with `python3 scripts/validate-eval-manifests.py`.
- Keep affected README files and router documentation aligned with inventory changes. Read counts from the generated catalog; avoid new hand-maintained totals.
- `router-main` is the universal entry point; domain routers own scenarios and journeys.
- `project-*` skills are self-contained. Cross-link only within the same project family unless the user explicitly approves an exception.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add vasilyu1983/ai-agents-public/frameworks/shared-skills/AGENTS.md@git:20260923.8dc5de4
Exact content
mdr add vasilyu1983/ai-agents-public/frameworks/shared-skills/AGENTS.md@sha256:128507f7540dbbf8

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ubi2dcnr62jxn3i7.svg)](https://markdownregistry.com/a/art_ubi2dcnr62jxn3i7)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260923.8dc5de4 latest2026-09-23 8dc5de4 6,238 BA view

Audit of the latest version

A  14 of 14 checks passed. Deterministic, no model, same answer every run.
  • pass: Size between 200 bytes and 200 KB (6238 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

vasilyu1983/ai-agents-public · 88 stars · license MIT · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ubi2dcnr62jxn3i7
GET https://markdownregistry.com/api/v1/resolve?ref=vasilyu1983/ai-agents-public/frameworks/shared-skills/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/128507f7540dbbf89d6c71d11835e40f69768abe2418ae44d61b52aa9351566b

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from vasilyu1983/ai-agents-public

agents-hooks skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/agents-hooks/SKILL.md · Configures Claude Code hooks and Codex hooks.json/notify callbacks. Use when adding guardrails, preflight, audit…
v1.5 · audit A · 88 stars
agents-mcp skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/agents-mcp/SKILL.md · Configures and hardens MCP servers for Claude Code and Codex agents. Use when connecting databases, APIs, files, or…
v1.5 · audit A · 88 stars
agents-memory skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/agents-memory/SKILL.md · Manages AGENTS.md, CLAUDE.md, and scoped repo rules for Claude Code and Codex. Use when fixing stale memory, ignored…
v1.4 · audit A · 88 stars
agents-skills-feedback-loop skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/agents-skills-feedback-loop/SKILL.md · Adds per-skill learnings loops for dated patterns, mistakes, and domain facts. Use when wiring skill memory…
v1.1 · audit A · 88 stars
agents-skills skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/agents-skills/SKILL.md · Creates and audits agent skills with SKILL.md, references, scripts, and platform-scoped metadata. Use when creating…
v1.2 · audit A · 88 stars
agents-swarm-orchestration skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/agents-swarm-orchestration/SKILL.md · Coordinates multi-agent execution across subagents, teams, and workflows. Use when planning dependency-aware fan-out…
v1.6 · audit A · 88 stars
ai-agents skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/ai-agents/SKILL.md · AI agent architecture, graph and loop composition, protocol choice, evaluation, and observability. Use when scoping or…
v1.1 · audit A · 88 stars
ai-architecture-advisor skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/ai-architecture-advisor/SKILL.md · Chooses among AI/ML approaches: classical ML, LLM, RAG, fine-tuning, agents, multimodal, embeddings/recsys…
v1.7 · audit A · 88 stars
ai-coding-agents-command-runtime skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/ai-coding-agents-command-runtime/SKILL.md · Designs slash-command runtimes for coding-agent CLIs. Use when modeling command registries, lazy loading, aliases…
v1.1 · audit A · 88 stars
ai-coding-agents-execution-sandbox skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/ai-coding-agents-execution-sandbox/SKILL.md · Designs execution sandboxes for coding agents. Use when modeling process isolation, filesystem policy, network…
v1.1 · audit B · 88 stars
ai-coding-agents-observability-evals skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/ai-coding-agents-observability-evals/SKILL.md · Designs coding-agent observability and evals. Use when measuring traces, replay, checkpoint lineage, quality…
v1.2 · audit A · 88 stars
ai-coding-agents-permissions skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/ai-coding-agents-permissions/SKILL.md · Designs approval and permission systems for coding-agent runtimes. Use when modeling tool approvals, plan-mode…
v1.1 · audit A · 88 stars

Every file in vasilyu1983/ai-agents-public

Browse by kind, by grade A, or by owner.