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 LandonSchropp/agent-toolkit --skill delegategit clone --depth 1 https://github.com/LandonSchropp/agent-toolkitWrote 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/landonschropp/agent-toolkit/delegate)<a href="https://agentmods.dev/skills/landonschropp/agent-toolkit/delegate"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/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/landonschropp/agent-toolkit/delegate"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/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 | $0.00039 | $0.00903 |
| Opus 5.5 | $0.00016 | $0.00361 |
| Sonnet 5.5 | $0.00008 | $0.00181 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade B, and why
delegate scanned grade B with 1 finding 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 today.
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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
Delegation is final. Say what was sent and where, then stop — never tell the user the agent will "report back" or "let you know" when it's done. Nothing it does flows back through this session; the user checks its progre How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegate
Hand a task to the environment best placed to do it. Choose the environment first; it decides everything else.
Choosing the Environment
Answer these in order and stop at the first that decides it:
- Is it engineering? If not, it goes to Non-Engineering. Visual design is Non-Engineering work done in Claude Design.
- Is it personal engineering? It goes to Local Engineering, since Cloud Engineering only takes work.
is-work-computertells you which machine you're on. - Can success be verified without the user's judgment? If so, and it doesn't need the user's Mac, it goes to Cloud Engineering. If it needs the Mac, the development environment, or the user's judgment as it goes (naming, UX, architecture designed in real time), it goes to Local Engineering.
Route by the task, never by where this session happens to be running. Your own environment changes how you reach a target, never which target gets the task. When the questions don't settle it, ask the user.
Skills
A skill that lives in a repository goes to Local Engineering: the one it is already in, or else personal-agent-toolkit when it's about managing the user's personal life or shouldn't be in a public repository, agent-toolkit when it's the user's own engineering tooling, and babylist/claude-plugins when it's for work. Non-Engineering's own skills are built and maintained there rather than delegated.
Writing the Prompt
The receiving agent has none of this conversation, and nothing it replies reaches you. A prompt saying "turn what we just did into a skill" is worthless to it. State, in the task's own terms:
- What the task is, in full. Where it came from a Linear issue, give the issue's URL rather than repeating its contents.
- What already happened that the agent needs to know, and where: repository, files, commits.
- What you have and have not already changed yourself, so it doesn't redo or undo work.
What ships with it
5 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.
- today Changed · +2 lines · -2 tokens per session 546c01a7d0bc
- 24d ago Changed 9afcb362f84f
- 25d ago Changed · -1 lines 5c1c47310e31
- 28d ago Changed · +5 lines scan A → B bfc2fdadcdd3
- 1mo ago Changed · +5 lines · +41 tokens per session 34c256847b21
- 1mo ago Changed 01291ac265fc
- 1mo ago Changed · -12 lines · -50 tokens per session fa9b6776632e
- 1mo ago Changed · +1 lines · +2 tokens per session 576550ecf1b5
- 1mo ago Changed · +2 lines c8a7a15bb6f5
- 1mo ago First seen · 49 lines · 48 tokens per session scan A 109d97946d37
delegate is a skill published in the GitHub repository LandonSchropp/agent-toolkit (3 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 903 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
cf-cli
Cloudflare's official cf CLI (beta) for the public Cloudflare API and Workers projects. Use for finding and running Cloudflare commands from the terminal — sign-in and profiles, cf cli search, cf schema, cf deploy/dev/build, resource commands for DNS, zones, D1, KV, and R2 — and for choosing between cf and Wrangler in…
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
find-journalists
Build a researched, fit-checked journalist list for a specific PR campaign. Prefer Medialyst's asynchronous media-list research workflow when available, with explicit approval before credit spend; otherwise produce a best-effort local list without guessed contacts.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
ai-visibility-writing
Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite its useful information. Use when someone asks for AI visibility, AI search, answer-engine, AEO, GEO, AI Overview, or…