ai-agent-readonly-context SKILL.md skillA
ai-agent-readonly-context from confighub/cub-scout is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add confighub/cub-scout/ai-agent-readonly-context@git:20261011.81f7574Pins git:20261011.81f7574 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- confighub/cub-scout
- Path
skills/ai-agent-readonly-context/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261011.81f7574, committed Oct 11, 2026
- First version recorded
- Sep 10, 2026
- Size
- 15,049 bytes
- Repository stars
- 14
- License
- MIT
Use when the user is WIRING CUB-SCOUT INTO AN AI AGENT (Claude / Codex / a custom LLM workflow) and needs the patterns for read-only context, MCP gateway tools, deterministic context snapshots, and the prompt-shape that makes cub-scout''s output reliable for LLMs. Natural phrasing: "set up cub-scout as a Claude tool", "expose cub-scout to my agent over MCP", "give the LLM a deterministic snapshot of this cluster", "what cub-scout patterns work well for AI agents?…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# ai-agent-readonly-context The agent-integration loop. The user is wiring cub-scout into an AI agent — Claude Code, Codex, Cursor, Continue, a custom MCP-aware LLM — and needs the patterns that make cub-scout's output reliable for LLMs. Three patterns matter here, plus the prompt shape that ties them together: 1. **MCP gateway** (`mcp serve`) — long-running tool surface the agent calls live 2. **context-pack** (`context-pack --format json`) — deterministic one-shot snapshot the agent reasons over 3. **`--presentation ai`** — output format with bracket notation + uppercase markers that LLMs parse reliably Plus the read-only invariant: every cub-scout tool an agent can call is **categorically non-mutating**. cub-scout is the safest possible AI surface because the worst-case prompt-injection still can't apply / edit / delete anything. ## When to use Explicit phrasings: - "Set up cub-scout as a Claude tool" - "Expose cub-scout to my agent over MCP" - "Give the LLM a deterministic snapshot of this cluster" - "What cub-scout patterns work well for AI agents?" - "MCP config for cub-scout in Claude Code / Codex / Cursor / Continue" …
Read the whole file at its exact version.
How to install
mdr add confighub/cub-scout/ai-agent-readonly-context@sha256:970a3762ef81d283The line at the top of this page pins the label git:20261011.81f7574, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_75rl4ovagvgwjtys)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Sep 10, 2026 and Oct 11, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261011.81f7574 latest | 2026-10-11 | 81f7574 | 15,049 B | A | view · diff |
| git:20261006.4415352 | 2026-10-06 | 4415352 | 14,352 B | A | view · diff |
| git:20260911.f36c91c | 2026-09-11 | f36c91c | 14,207 B | A | view · diff |
| git:20260911.6cf13e0 | 2026-09-11 | 6cf13e0 | 14,137 B | A | view · diff |
| git:20260910.a2f712d | 2026-09-10 | a2f712d | 13,884 B | A | view · diff |
| git:20260910.df76e93 | 2026-09-10 | df76e93 | 13,829 B | A | view · diff |
| git:20260910.e36f2e2 | 2026-09-10 | e36f2e2 | 13,420 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (15049 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
confighub/cub-scout · 14 stars · license MIT · pushed 2026-10-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_75rl4ovagvgwjtys GET https://markdownregistry.com/api/v1/resolve?ref=confighub/cub-scout/ai-agent-readonly-context GET https://markdownregistry.com/api/v1/blob/970a3762ef81d283b95a19175c404008e501d780e55d6558980feedcf5112dea
Your AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.