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 abstractonion/cadence --skill delegate-with-fresh-contextgit clone --depth 1 https://github.com/abstractonion/cadenceWrote 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/abstractonion/cadence/delegate-with-fresh-context)<a href="https://agentmods.dev/skills/abstractonion/cadence/delegate-with-fresh-context"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/delegate-with-fresh-context/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/abstractonion/cadence/delegate-with-fresh-context"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/delegate-with-fresh-context.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 | $0.00036 | $0.00496 |
| Opus 5 | $0.00018 | $0.00248 |
| Sonnet 5 | $0.00007 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
delegate-with-fresh-context 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.
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.
Delegate with fresh context
When a task is well-scoped and doesn't need the running conversation to succeed, hand it off to a fresh subagent. The subagent gets a clean context window and exactly what it needs; your main context stays lean and focused on orchestration.
When to delegate
- The task is independent — a self-contained bug fix, a focused refactor, one piece of investigation that doesn't depend on conversation history.
- The work is parallelizable — multiple independent failures, investigations, or build tasks can run concurrently rather than sequentially.
- The task would otherwise pull large files, long stack traces, or unrelated history into the main context just to do one thing.
What the brief must include
- Goal. One sentence stating what success looks like.
- Scope. Exact files or directories the subagent should touch or read. Constrain what it must NOT change.
- Context. Paste the specific snippets, errors, or facts it needs — don't make it re-derive what you already know by re-reading large files.
- Expected output. Concrete: a fix plus a passing test, a summary with
file:linereferences, a list of root causes.
What not to do
- Don't dispatch a subagent with "figure out what's wrong" and no scope — it will get lost.
- Don't dispatch parallel subagents that touch the same files — they'll conflict. Same branch with disjoint scopes: partition per
parallel-workstreamsfirst. - Don't trust a subagent's "done" report without checking the diff and re-running its verification fresh (see
verify-with-runtime).
After it returns
Integrate the work the same way you'd review your own diff (see self-review-before-handoff): quote evidence, run the verification fresh, surface scope drift, and resolve conflicts before claiming done.
Multiple subagents on the same branch. When two or more subagents have returned on one branch, do not claim done from per-stream reports alone. Run verify-parallel-integration on the combined diff: survey overlaps and wiring, resolve duplicate registrations, then run lint, typecheck, and tests fresh (see verify-with-runtime).
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.
- 9d ago First seen · 34 lines · 36 tokens per session scan A c1ae6762a978
delegate-with-fresh-context is a skill published in the GitHub repository abstractonion/cadence (4 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 496 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…