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.
npx skills add dryvist/claude-code-plugins --skill delegation-laddergit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWrote 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.
[](https://agentmods.dev/skills/dryvist/claude-code-plugins/delegation-ladder)<a href="https://agentmods.dev/skills/dryvist/claude-code-plugins/delegation-ladder"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/delegation-ladder/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.
<a href="https://agentmods.dev/skills/dryvist/claude-code-plugins/delegation-ladder"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/delegation-ladder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00023 | $0.00787 |
| Opus 5.5 | $0.00009 | $0.00315 |
| Sonnet 5.5 | $0.00005 | $0.00157 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
delegation-ladder 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegation ladder
Use this ladder for delegation across Claude Code, Codex, and OpenCode. Keep scope, security decisions, final verification, and merging with the trusted caller.
Route selection
Classify the task and content first, then take the first rung that qualifies:
| Kind | Ladder | ZCode use |
|---|---|---|
code-review |
Codex -> ZCode -> OpenCode Go -> Haiku high | Public coding overflow and a separate review from another model family when selected by the route |
triage |
ZCode Flash -> Codex -> Haiku high | Bulk reading and triage of public material |
private |
Codex -> OpenCode Go -> Haiku high | Never eligible for ZCode |
Codex qualifies while codex-quota exits 0. ZCode qualifies for a public
repository in the allowlist below; zcode-job start refuses anything else.
Treat a Z.ai quota or 429 error as exhausted for the rest of the session and
take the next rung. Do not skip a rung. When no rung qualifies,
stop and notify the operator.
Treat a missing repository, unknown visibility, absent owner approval, or
missing local dispatcher approval as private. ZCode is limited to public
repositories owned by dryvist, JacobPEvans, or JacobPEvans-personal that
also appear in the installed client subset. Never send secrets, credentials,
private repository content, live infrastructure work, or privileged actions
to ZCode. Use the private route for private material. Review task text,
attachments, diffs, logs, and conversation context before submission.
Execute the selected route
codex: use the configured Codex CLI or MCP route.zcodeorzcode-flash: drive the existingzcode-jobclient (below).opencode-go: use the configured OpenCode Go route.haiku-high: use the high effort Haiku subagent.stop: stop and notify the operator.
For ZCode work, write a bounded prompt with the allowed scope, the repository default branch, and acceptance criteria. Then run:
zcode-job repos # approved repositories
zcode-job start <owner/repo> "<prompt>" # prints the job id
zcode-job status <job-id> # repeat until succeeded, failed, cancelled, or timeout
zcode-job result <job-id>
zcode-job cancel <job-id> # when the deadline passes
What ships with it
2 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.
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 · 73 lines · 23 tokens per session scan A 20c7c8464f86
delegation-ladder is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 787 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-14.
Other skills, from other repositories
generic-fullstack-code-reviewer
Review full-stack code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md compliance. Enforces TypeScript strict mode, input validation, GPU-accelerated animations, and design system consistency. Use when completing features, before commits, or reviewing pull requests.
generic-static-code-reviewer
Review static site code for bugs, security issues, performance problems, accessibility gaps, and CLAUDE.md compliance. Enforces pure HTML/CSS/JS standards, minimal page weight, mobile-first design. Use when completing features, before commits, or reviewing changes.
review
Code review with semantic diffs, expert routing, and auto-TaskCreate. Triggers on: code review, review changes, check code, review PR, security audit.
structural-search
Search code by AST structure using ast-grep. Find semantic patterns like function calls, imports, class definitions instead of text patterns. Triggers on: find all calls to X, search for pattern, refactor usages, find where function is used, structural search, ast-grep, sg.
ai-architect-review
Review the architecture of a system that calls a language model. Use when adding an agent loop, a retrieval path, a tool surface, or an MCP server to a codebase; when a system that worked in a demo is being prepared for production; or when asked to audit, review, or plan AI/agent architecture. Checks the four…
github-code-review
Comprehensive GitHub pull-request code review with multi-agent coordination. Use when reviewing a PR or diff, auditing changes for correctness/security/style before merge, or generating actionable inline review comments.