askit-build-subagent

askit-build-subagent is a skill for Claude Code from product-on-purpose/agent-skills-toolkit. It costs 59 tokens per session (930 once invoked), scanned A, original, Apache-2.0.

A tool for creating or improving Claude subagents, which are delegated assistants described in agents/*.md files. It defines their role, tools, and permitted component chain.

In plain words
What is it for?
Use it to scaffold a new subagent, declare its tools and model, specify which components it may call, or improve an existing agent file.
Why use it?
It helps keep delegated assistants narrowly scoped and consistent with the required authoring standard.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Part of the agent-skills-toolkit plugin — 27 skills, 2 commands, 7 agents, 1 hook, 1 plugin shipped together

Good fit Use it to scaffold a new subagent, declare its tools and model, specify which components it may call, or improve an existing agent file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/product-on-purpose/agent-skills-toolkit/askit-build-subagent
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.

Any agent
npx skills add product-on-purpose/agent-skills-toolkit --skill askit-build-subagent
Clone the repo
git clone --depth 1 https://github.com/product-on-purpose/agent-skills-toolkit

Made for: Claude Code.

Or install agent-skills-toolkit, the plugin that ships this one along with the rest of its 27 skills, 2 commands, 7 agents, 1 hook, 1 plugin.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for askit-build-subagent

README.md
[![agentmods](https://agentmods.dev/badge/skills/product-on-purpose/agent-skills-toolkit/askit-build-subagent/github.svg)](https://agentmods.dev/skills/product-on-purpose/agent-skills-toolkit/askit-build-subagent)
Your own site
<a href="https://agentmods.dev/skills/product-on-purpose/agent-skills-toolkit/askit-build-subagent"><img src="https://agentmods.dev/badge/skills/product-on-purpose/agent-skills-toolkit/askit-build-subagent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for askit-build-subagent

Your own site · 80×15
<a href="https://agentmods.dev/skills/product-on-purpose/agent-skills-toolkit/askit-build-subagent"><img src="https://agentmods.dev/badge/skills/product-on-purpose/agent-skills-toolkit/askit-build-subagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 930 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00930
Opus 5 $0.00030 $0.00465
Sonnet 5 $0.00012 $0.00186
Haiku 4.5 $0.00006 $0.00093

Measured 12d ago against content hash 22734d90267a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

askit-build-subagent 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 12d 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.

skills/askit-build-subagent/SKILL.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

askit-build-subagent

Purpose

Author conformant subagents. Two modes: create scaffolds a new agents/<name>.md (frontmatter + role body); improve raises an existing subagent toward the quality bar. Subagents are Claude-only for plugin distribution (Codex v0.135 plugins cannot ship [agents.*]; Standard sec 3.3), so this skill emits no Codex artifact. Authoring depth is in references/authoring-subagents.md.

When to use

When the user asks to create, scaffold, write, or improve a subagent (an agents/<name>.md delegate).

create mode

  1. Brief interview: ask for the subagent name (kebab-case), the bounded job it owns, the narrowest tools it needs, and which components (if any) it may invoke. Skip the interview if these inputs are already in context.
  2. Copy templates/agent.md into agents/<name>.md.
  3. Fill the frontmatter: name equal to the file basename; a description that states what AND when (Standard sec 8.1); tools as the narrowest set (sec 9); optional model; metadata.chain naming the components it may invoke as a comma-separated string (the recommended shape - a YAML list is silently coerced to a string repr by the reference implementation, see authoring-chain-contracts.md; omit chain if there is none); metadata.version, metadata.tier, metadata.status, and metadata.agent-targets: [claude] (sec 3.3 - subagents are Claude-only for plugin distribution).
  4. Do not write hooks, mcpServers, or permissionMode. Claude Code states plainly that "for security reasons, hooks, mcpServers, and permissionMode are not supported for plugin-shipped agents" (plugins reference, read 2026-08-12). Writing one does not configure anything; the runtime refuses it, and the author is left believing otherwise. The supported set is name, description, model, effort, maxTurns, tools, disallowedTools, skills, memory, background, and isolation (whose only valid value is worktree). Marketplace scope reports this across every member of a catalogue.
  5. Register the subagent in library.json components.subagents as { name, path, version, tier, status }.
  6. If the subagent declares a chain, add the entry to agents/_chain-permitted.yaml (<name>: [<invoked>, ...]) so S4 has no orphan.
  7. Assess with node scripts/evaluate.mjs . --json and iterate until 0 errors (S3 components index + S4 chain contract must be clean).

Read the full file on GitHub · 34 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 12d ago First seen · 34 lines · 59 tokens per session scan A 22734d90267a

Subscribe to this mod's changes

askit-build-subagent is a skill published in the GitHub repository product-on-purpose/agent-skills-toolkit (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 930 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

modelchk

Size a task's run before spending it: the cheapest sufficient capability tier (fast, standard, frontier) and the reasoning effort within it, on a neutral scale that binds to whatever levels the model exposes. Use when work seems over- or under-powered, costly, ambiguous, or high-risk, or asks which model class and how…

LilMGenius/paperthin · 74 tokens

autobahn

Carve guardrail-adjacent items out of scope with safe alternatives before risk-adjacent work starts, then run the safe remainder at full strength in a fresh subagent that only ever sees the carved prompt, never the risky input. Use when a task includes stealth, scraping, privacy, IP, policy, licensing, security, or…

LilMGenius/paperthin · 129 tokens

re0-release

Walk a pending change through this repo's shipping and releasing checklist end to end, then tag and publish once confirmed. User-invoked: run it when you've decided to ship.

LilMGenius/paperthin · 40 tokens

ssotize

Audit and consolidate a fact that's scattered across places into one canonical source, after approval, and replace the rest with references. Use when asked to find duplication, check consistency, locate the source of truth, deduplicate, consolidate, unify, or establish SSOT across artifacts or platforms. Starts…

LilMGenius/paperthin · 78 tokens

re0-plan

Open a paperthin iteration's casebook before re0-loop's first turn — seeded with real content the moment the folder exists, never an empty directory. User-invoked, paperthin-only: assumes the full skill package installed. Run when opening a new build cycle in this repo.

LilMGenius/paperthin · 62 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens