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 TweekFawkes/prompts --skill delegategit clone --depth 1 https://github.com/TweekFawkes/promptsWrote 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/tweekfawkes/prompts/delegate)<a href="https://agentmods.dev/skills/tweekfawkes/prompts/delegate"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/delegate/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/tweekfawkes/prompts/delegate"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/delegate.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 | $0.00057 | $0.01136 |
| Opus 5.5 | $0.00023 | $0.00454 |
| Sonnet 5.5 | $0.00011 | $0.00227 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
delegate 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 1mo 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Route $ARGUMENTS to the cheapest capable delegate, then read back only a receipt.
Routing table
- Plan, decompose, or judge a tradeoff: stay in the primary session (Fable 5.1). Do not delegate this.
- Implement one ticket: the
workersubagent (Sonnet 5) via the Agent tool. - Review a diff before
/ship: thereviewersubagent (Opus 5) via the Agent tool. - A hard or ambiguous ticket the worker default can't crack:
workerwith a model override to Opus. - Independent second opinion on a design or a review:
grok(Grok 4.6), orcodex exec(GPT-6 Astra). - Cheaper second opinion or bulk generation when GPT-6 Astra is overkill:
codex execwith GPT-5.6 Sol (strongest), Terra, or Luna (cheapest) — same CLI, smaller model. - Bulk cheap/offline text work (summaries, boilerplate, log triage):
opencode runagainst a self-hosted vLLM (or other OpenAI-compatible) endpoint configured as a provider in~/.config/opencode/opencode.json. - Trivial lookup, cheapest Claude: Agent tool with
model: haiku, or shellclaude -p "<prompt>" --model claude-haiku-4-5-20251001 --permission-mode bypassPermissions --output-format text.
Prefer the Agent tool (worker, reviewer) over shelling out — it shares context, no process
bookkeeping. Shell out only for another vendor's model or a deliberately separate process/worktree.
Prompt shape for any delegate
Write the prompt to a file and pass it as "$(cat prompt.txt)"; claude -p also accepts it on
stdin (claude -p ... < prompt.txt).
GOAL: <one sentence, the shippable outcome>
FILES: <exact paths to read/edit, nothing else>
ACCEPTANCE: <one command and the expected result>
STOP: <when to stop; three failed rounds on the same failure = blocked, report it>
The user is away. Never ask a question — decide, state the assumption, continue.
OUTPUT: receipt <=150 words (STATUS/CHANGED/CHECKS/ASSUMED/BLOCKER); write anything longer to <path>.
Verified one-liners
Each run must be given the worktree path explicitly — none of these infer it.
What ships with it
1 file 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.
- 1mo ago First seen · 82 lines · 57 tokens per session scan A cff5334a008f
delegate is a skill published in the GitHub repository TweekFawkes/prompts (2 stars, last pushed 1mo ago), licensed Unlicense. It adds 57 tokens to every session and 1,136 once invoked, about $0.0002 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 2026-09-20.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…