circular-safe-tool-registry-loading

circular-safe-tool-registry-loading is a skill for Claude Code, Codex from ychampion/cskill-agents. It costs 25 tokens per session (422 once invoked), scanned A, original, MIT.

A guide for assembling a software tool registry when optional tools may depend on one another or take time to start.

In plain words
What is it for?
Use it to add optional tools through lazy loaders, apply feature switches, and keep the registry order predictable.
Why use it?
It avoids circular loading problems and prevents disabled tools from being initialised unnecessarily.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to add optional tools through lazy loaders, apply feature switches, and keep the registry order predictable.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ychampion/cskill-agents/circular-safe-tool-registry-loading
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 ychampion/cskill-agents --skill circular-safe-tool-registry-loading
Clone the repo
git clone --depth 1 https://github.com/ychampion/cskill-agents

Made for: Claude Code, Codex.

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 circular-safe-tool-registry-loading

README.md
[![agentmods](https://agentmods.dev/badge/skills/ychampion/cskill-agents/circular-safe-tool-registry-loading/github.svg)](https://agentmods.dev/skills/ychampion/cskill-agents/circular-safe-tool-registry-loading)
Your own site
<a href="https://agentmods.dev/skills/ychampion/cskill-agents/circular-safe-tool-registry-loading"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/circular-safe-tool-registry-loading/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 circular-safe-tool-registry-loading

Your own site · 80×15
<a href="https://agentmods.dev/skills/ychampion/cskill-agents/circular-safe-tool-registry-loading"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/circular-safe-tool-registry-loading.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 422 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 $0.00025 $0.00422
Opus 5 $0.00013 $0.00211
Sonnet 5 $0.00005 $0.00084
Haiku 4.5 $0.00003 $0.00042

Measured 9d ago against content hash 5746cdc3fead, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

circular-safe-tool-registry-loading 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 9d 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.

agents/claude-code/skills/circular-safe-tool-registry-loading/SKILL.md · 29 lines

What it actually says

SKILL: Circular-Safe Tool Registry Loading

Domain: Tool Orchestration
Trigger: Use when optional tools depend on the main registry or on each other, and eager imports would create cycles or unnecessary startup work.
Source Pattern: Distilled from reviewed tool execution, streaming, persistence, and output-budget implementations.

Core Method

Keep registry assembly as a simple ordered list, but place any cyclic or expensive tool behind a tiny lazy loader. That loader imports and constructs the tool only when the registry is being composed and the relevant feature is enabled. The loader returns either one tool or nothing, and the registry flattens those results in a stable order. This breaks circular dependency chains, keeps disabled features cold, and preserves one authoritative registry surface.

Key Rules

  • Wrap any tool that would trigger a cycle or heavy initialization in a zero-argument lazy loader.
  • Apply the same feature gate at the loader boundary so disabled tool branches never initialize.
  • Keep registry assembly deterministic: each loader should return one tool or no value, and the final list should preserve a fixed order.
  • Document why each lazy loader exists so future maintainers do not inline it and reintroduce the cycle.

Example Application

If a collaborative workspace tool depends on the same registry module that is trying to list it, move that tool behind a lazy loader and call the loader only when the collaboration feature is enabled. The registry still exposes the full surface, but startup no longer hits a circular import.

Anti-Patterns (What NOT to do)

  • Don’t import mutually dependent tools at the top level of both modules; that recreates the cycle you are trying to avoid.
  • Don’t hide feature gating deep inside tool constructors; keep the gating decision at the registry edge.
  • Don’t instantiate the same optional tool from multiple ad hoc call sites; let one registry pass own ordering and construction.
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. 9d ago First seen · 29 lines · 25 tokens per session scan A 5746cdc3fead

Subscribe to this mod's changes

circular-safe-tool-registry-loading is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 422 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 2026-08-30.