A command for creating a new coding-agent skill inside the current project using Agent Plugin Kit. A skill is a reusable instruction set that teaches an agent how to perform a particular job.

Use it to create a skill skeleton, describe when the skill should run, and add scripts or reference material it needs. It keeps the project foundation and agent instructions managed by the toolkit.

It provides a consistent starting structure and prevents setup files from being created inconsistently or duplicated. It also helps clarify what the new skill should do before building it.

inherit — Command by lxb12123

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/lxb12123/agent-plugin-kit/inherit

Clone the repo

git clone --depth 1 https://github.com/lxb12123/agent-plugin-kit

Or install agent-plugin-kit, the plugin that ships this one along with the rest of its 3 commands, 2 hooks, 1 MCP server, 1 plugin.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 761 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00022	$0.00761
Opus 5	$0.00011	$0.00380
Sonnet 5	$0.00004	$0.00152
Haiku 4.5	$0.00002	$0.00076

Measured 2d ago against content hash 5bf0c4de943f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

inherit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/inherit.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/inherit — Grow a gene-compliant skill

Your task: inside the current project, use Agent Plugin Kit's deterministic engine to idempotently imprint the foundation and grow the skill the user wants. The engine lives at ${CLAUDE_PLUGIN_ROOT}/lib/cli.mjs. Do not manually create .gene/ or edit AGENTS.md — the engine handles these, guaranteeing idempotency.

Flow

Understand the intent: talk with the user to figure out what this skill should do. Clarify:
- What problem does the skill solve? (one sentence)
- The skill name (kebab-case, e.g. review, changelog)?
- Does it need deterministic scripts? What reference knowledge does it need?
Generate a compliant skeleton (build it with the engine so the structure is always compliant):
```
TMP=$(mktemp -d)
node "${CLAUDE_PLUGIN_ROOT}/lib/cli.mjs" scaffold "$TMP" --name <name>
```
Generates skill.yaml (with when-to-use + the uses: self-description block), prompt.md, scripts/, and reference/.
Fill in the content: edit the files under $TMP:
- skill.yaml: fill in description and when-to-use; if it uses mcp/permissions/subagents, declare them under uses:.
- prompt.md: spell out what the LLM should do and produce.
- Put deterministic steps in scripts/*.mjs (0 token), and on-demand knowledge in reference/*.md.
Imprint into the project (the engine handles idempotency):
```
node "${CLAUDE_PLUGIN_ROOT}/lib/cli.mjs" inherit . --name <name> --from "$TMP"
```
The engine: imprints the foundation if absent (.gene/, GENE.md, skills/) → installs the skill idempotently by fingerprint → updates .gene/gene.json → recompiles AGENTS.md.
Report the result: relay the JSON the engine outputs (stamped / skill.changed / compiledSkills); skill.changed=false means the skill already exists and is unchanged (idempotent, no rewrite).
Point to the next step: inherit only grows the skill into the project — it does NOT package an installable plugin. Tell the user: if they want to ship this as an installable, multi-host plugin (with .claude-plugin/ manifest, plugin-root SKILL.md, commands/, and a generated README.md), run pack:
```
node "${CLAUDE_PLUGIN_ROOT}/lib/cli.mjs" pack .
```
Or do both in one step by re-running with --target plugin. Skip this if they only want to use the skill locally.

Read the full file on GitHub · 49 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 49 lines · 22 tokens per session scan A 5bf0c4de943f

Subscribe to this mod's changes

inherit is a command published in the GitHub repository lxb12123/agent-plugin-kit (1 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 761 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents agent-skills agents ai-agents claude-code claude-code-plugin codex

template

Manage issue templates for streamlined issue creation.

gastownhall/beads · 0 tokens

cross-validate

Take a specific scientific claim and confirm or refute it across 3+ independent databases, then report concordance. Use before publishing, citing, or acting on a fact when you want to know how strongly it's supported. Forces multi-source verification that the agent doesn't naturally enforce.

mims-harvard/ToolUniverse · 59 tokens

translate-id

Resolve an identifier across all relevant namespaces (HGNC symbol, Ensembl, UniProt, NCBI Gene ID, RefSeq, MGI, OMIM, ChEMBL, PubChem, etc.). Detects the input namespace automatically, picks the right resolver tool, and returns a complete cross-reference table. Use when you have an ID in one namespace and need it in…

mims-harvard/ToolUniverse · 85 tokens

inherit