How do I install the Askit Build Chain Contract skill?

Run npx skillmds@latest add product-on-purpose/askit-build-chain-contract in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Askit Build Chain Contract safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Askit Build Chain Contract?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Askit Build Chain Contract free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Askit Build Chain Contract?

product-on-purpose (@product-on-purpose) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Askit Build Chain Contract by product-on-purpose

Name: Askit Build Chain Contract
Author: product-on-purpose

Askit Build Chain Contract

Creates and improves a plugin's chain contract (agents/_chain-permitted.yaml) to the Advanced Skill Library Standard. Use when a skill or subagent invokes another component and you need to declare the permitted inter-component invocations, or to resolve S4 orphan or phantom findings.

File contents

askit-build-chain-contract

Purpose

Author a plugin's chain contract: the explicit declaration of which components may invoke which others (Standard sec 3.6). A chain contract is a CONDITIONAL MUST - required if and only if a component invokes another, so a plugin with no inter-component invocation ships no contract (no empty governance files). Two modes: create authors agents/_chain-permitted.yaml (and the optional agents/_pairing.yaml); improve resolves S4 findings. Authoring depth is in references/authoring-chain-contracts.md. Follows the shared builder contract (../../docs/reference/builder-pattern.md).

When to use

When a skill or subagent declares a chain: to another component and you need to permit it, or when evaluate reports an S4 orphan (an invocation not permitted) or phantom (a contract entry naming a missing component).

create mode

Scan components for chain: declarations (which caller invokes which callees). Skip the contract entirely if nothing chains (the conditional MUST).
Author agents/_chain-permitted.yaml: one entry per caller, listing the components it may invoke. Copy templates/chain-permitted.yaml if none exists.
Optionally author agents/_pairing.yaml for recommended (not required) skill plus subagent pairings.
Evaluate (node scripts/evaluate.mjs . --json) until S4 is clean: every chain: invocation is permitted (no orphan) and every contract entry names an on-disk component (no phantom).

improve mode

Run node scripts/evaluate.mjs . --json and read the S4 findings.
For an orphan, add the missing caller: [callee] permission. For a phantom, fix the misspelled name, remove the stale entry, or create the missing component.
Re-run to confirm S4 is clean.

Scope

The contract is agent-agnostic: one agents/_chain-permitted.yaml (no per-target form). It binds exactly when there is an invocation to make safe (sec 3.6), so it is a safety mechanism, not ceremony. S4 (chain-contract integrity) flags orphans and phantoms; do not ship an empty contract for a plugin that does not chain.

---name: askit-build-chain-contractdescription: Creates and improves a plugin's chain contract (agents/_chain-permitted.yaml) to the Advanced Skill Library Standard. Use when a skill or subagent invokes another component and you need to declare the permitted inter-component invocations, or to resolve S4 orphan or phantom findings.---# askit-build-chain-contract## PurposeAuthor a plugin's chain contract: the explicit declaration of which components may invoke which others (Standard sec 3.6). A chain contract is a CONDITIONAL MUST - required if and only if a component invokes another, so a plugin with no inter-component invocation ships no contract (no empty governance files). Two modes: `create` authors `agents/_chain-permitted.yaml` (and the optional `agents/_pairing.yaml`); `improve` resolves S4 findings. Authoring depth is in [references/authoring-chain-contracts.md](references/authoring-chain-contracts.md). Follows the shared builder contract ([../../docs/reference/builder-pattern.md](../../docs/reference/builder-pattern.md)).## When to useWhen a skill or subagent declares a `chain:` to another component and you need to permit it, or when `evaluate` reports an S4 orphan (an invocation not permitted) or phantom (a contract entry naming a missing component).## create mode1. Scan components for `chain:` declarations (which caller invokes which callees). Skip the contract entirely if nothing chains (the conditional MUST).2. Author `agents/_chain-permitted.yaml`: one entry per caller, listing the components it may invoke. Copy `templates/chain-permitted.yaml` if none exists.3. Optionally author `agents/_pairing.yaml` for recommended (not required) skill plus subagent pairings.4. Evaluate (`node scripts/evaluate.mjs . --json`) until S4 is clean: every `chain:` invocation is permitted (no orphan) and every contract entry names an on-disk component (no phantom).## improve mode1. Run `node scripts/evaluate.mjs . --json` and read the S4 findings.2. For an orphan, add the missing `caller: [callee]` permission. For a phantom, fix the misspelled name, remove the stale entry, or create the missing component.3. Re-run to confirm S4 is clean.## ScopeThe contract is agent-agnostic: one `agents/_chain-permitted.yaml` (no per-target form). It binds exactly when there is an invocation to make safe (sec 3.6), so it is a safety mechanism, not ceremony. S4 (chain-contract integrity) flags orphans and phantoms; do not ship an empty contract for a plugin that does not chain.

Frequently asked questions