Install
$ agentstack add skill-product-on-purpose-agent-skills-toolkit-askit-build-subagent ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
askit-build-subagent
Purpose
Author conformant subagents. Two modes: create scaffolds a new agents/.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](references/authoring-subagents.md).
When to use
When the user asks to create, scaffold, write, or improve a subagent (an agents/.md delegate).
create mode
- 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.
- Copy
templates/agent.mdintoagents/.md. - Fill the frontmatter:
nameequal to the file basename; adescriptionthat states what AND when (Standard sec 8.1);toolsas the narrowest set (sec 9); optionalmodel;chainlisting components it may invoke (omit if none);metadata.version,metadata.tier,metadata.status, andmetadata.agent-targets: [claude](sec 3.3 - subagents are Claude-only for plugin distribution). - Register the subagent in
library.jsoncomponents.subagentsas{ name, path, version, tier, status }. - If the subagent declares a
chain, add the entry toagents/_chain-permitted.yaml(: [, ...]) so S4 has no orphan. - Assess with
node scripts/evaluate.mjs . --jsonand iterate until 0 errors (S3 components index + S4 chain contract must be clean).
improve mode
- Run
node scripts/evaluate.mjs . --jsonand read the report. - For each finding: an S3 error -> declare/undeclare the subagent in
components.subagentsto match disk; an S4 orphan -> add the missingcaller -> calleetoagents/_chain-permitted.yaml; an S4 phantom (the contract names a component not on disk) -> remove that contract entry, fix a misspelled name, or create the missing component. For any other finding, read its message and apply the fix it states. - Re-run evaluate to confirm.
Scope
Claude-only: a subagent is agents/.md (Claude auto-discovers it). Codex does not ingest plugin-shipped subagents (Standard sec 3.3), so there is no Codex render. Authoring is performed inline by the running agent; the toolkit's own askit-skill-author subagent is the delegated authoring role for skills.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: product-on-purpose
- Source: product-on-purpose/agent-skills-toolkit
- License: Apache-2.0
- Homepage: https://product-on-purpose.github.io/agent-skills-toolkit
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.