subagent-engineering SKILL.md skillA

subagent-engineering from xobotyi/cc-foundry is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add xobotyi/cc-foundry/subagent-engineering@git:20261029.ffe0c27

Pins git:20261029.ffe0c27 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
xobotyi/cc-foundry
Path
plugins/ai-helpers/skills/subagent-engineering/SKILL.md
Versions recorded
5
Latest version
git:20261029.ffe0c27, committed Oct 29, 2026
First version recorded
Aug 17, 2026
Size
12,376 bytes
Repository stars
23
License
MIT

Design and maintain Claude Code subagents: the delegation decision, the frontmatter that governs a run, and the system prompt the agent wakes up with.

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

**A subagent is a separate context with its own system prompt.** It inherits none of the caller's conversation, and
everything it reads is discarded when it stops — only what it returns survives. Isolation is the reason to pay for one,
and the return value is the entire product.

<prerequisite>
A subagent definition is a system prompt. Invoke `prompt-engineering` for the wording, instruction budget, and
timelessness rules that govern every line written here. This skill covers only what is specific to the subagent
artifact — the delegation decision, the frontmatter, and the prompt the agent wakes up with.
</prerequisite>

## Delegate only where the isolation pays

- **Delegate work whose output is far larger than its conclusion** — a wide search, a long file, a verbose test run. The
  caller pays for the summary instead of the transcript.
- **Delegate to restrict, too.** A tool allowlist or a cheaper model binds the whole run, which no instruction inside
  the main conversation achieves.
- **Keep the work in the main conversation when it needs back-and-forth**, when several phases share the same context,
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add xobotyi/cc-foundry/subagent-engineering@sha256:3110795dbc0efd4f

The line at the top of this page pins the label git:20261029.ffe0c27, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_udbsdjm3p2hwnpu2.svg)](https://markdownregistry.com/a/art_udbsdjm3p2hwnpu2)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Aug 17, 2026 and Oct 29, 2026, about one every 18 days.

versioncommittedcommitsizeaudit
git:20261029.ffe0c27 latest2026-10-29 ffe0c27 12,376 BA view · diff
git:20260828.330cbc22026-08-28 330cbc2 11,909 BA view · diff
git:20260828.2e38d3c2026-08-28 2e38d3c 14,547 BA view · diff
git:20260823.ef9cec42026-08-23 ef9cec4 14,609 BA view · diff
git:20260817.c823ba72026-08-17 c823ba7 11,579 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (12376 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

xobotyi/cc-foundry · 23 stars · license MIT · pushed 2026-10-31 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_udbsdjm3p2hwnpu2
GET https://markdownregistry.com/api/v1/resolve?ref=xobotyi/cc-foundry/subagent-engineering
GET https://markdownregistry.com/api/v1/blob/3110795dbc0efd4f4b027d6387d3b70d17d73dc9fe4310cb44a633209ae55f6d

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.

More from xobotyi/cc-foundry

release SKILL.md skill
xobotyi/cc-foundry · .claude/skills/release/SKILL.md · GitHub release creation for cc-foundry plugins: per-plugin tags, release notes as the changelog, and post-merge…
git:20261029.d1dffd8 · audit A · 23 stars
CLAUDE.md CLAUDE.md file
xobotyi/cc-foundry · CLAUDE.md
git:20261029.800e877 · audit A · 23 stars
CLAUDE.md@plugins/ai-helpers CLAUDE.md file
xobotyi/cc-foundry · plugins/ai-helpers/CLAUDE.md
git:20261026.441701b · audit A · 23 stars
output-style-engineering SKILL.md skill
xobotyi/cc-foundry · plugins/ai-helpers/skills/output-style-engineering/SKILL.md · Design and maintain Claude Code output styles: choosing the mechanism, setting the frontmatter, and writing the role…
git:20260829.245c665 · audit A · 23 stars
prompt-engineering SKILL.md skill
xobotyi/cc-foundry · plugins/ai-helpers/skills/prompt-engineering/SKILL.md · Write and debug instruction text on any surface: requests, standing context such as CLAUDE.md, tool and schema…
git:20260828.1bf32f2 · audit A · 23 stars
prompt-terser SKILL.md skill
xobotyi/cc-foundry · plugins/ai-helpers/skills/prompt-terser/SKILL.md · Run a phased terseness pass over an existing prompt or skill and return a diff-proposal: mechanical wording and format…
git:20260828.1bf32f2 · audit A · 23 stars
skill-engineering SKILL.md skill
xobotyi/cc-foundry · plugins/ai-helpers/skills/skill-engineering/SKILL.md · Author and maintain Agent Skills: routing metadata, body content, bundled references and scripts, evaluation, and…
git:20260828.4127f54 · audit A · 23 stars
CLAUDE.md@plugins/backend CLAUDE.md file
xobotyi/cc-foundry · plugins/backend/CLAUDE.md
git:20260830.16ec660 · audit A · 23 stars
observability SKILL.md skill
xobotyi/cc-foundry · plugins/backend/skills/observability/SKILL.md · Observability discipline: structured logging, metrics instrumentation, distributed tracing, and signal correlation…
git:20261028.323c887 · audit A · 23 stars
otel-tracing SKILL.md skill
xobotyi/cc-foundry · plugins/backend/skills/otel-tracing/SKILL.md · OpenTelemetry tracing discipline: correct spans, propagation, and semantic conventions produce useful traces. Invoke…
git:20260517.e6c4538 · audit A · 23 stars
prometheus SKILL.md skill
xobotyi/cc-foundry · plugins/backend/skills/prometheus/SKILL.md · Prometheus instrumentation discipline: right metric type, right name, right labels. Invoke whenever task involves any…
git:20260517.e6c4538 · audit A · 23 stars
statsd SKILL.md skill
xobotyi/cc-foundry · plugins/backend/skills/statsd/SKILL.md · StatsD metric instrumentation: push metrics over UDP, choose the right metric type, name consistently. Invoke whenever…
git:20260517.e6c4538 · audit A · 23 stars

Every file in xobotyi/cc-foundry

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