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 agentmods add skills/ohong/agent-skills/delegatenpx skills add ohong/agent-skills --skill delegategit clone --depth 1 https://github.com/ohong/agent-skillsWrote 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/ohong/agent-skills/delegate)<a href="https://agentmods.dev/skills/ohong/agent-skills/delegate"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/delegate.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.01024 |
| Opus 5 | $0.00028 | $0.00512 |
| Sonnet 5 | $0.00011 | $0.00205 |
| Haiku 4.5 | $0.00006 | $0.00102 |
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 3d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegate
Three roles:
| Role | Model | Job |
|---|---|---|
| General (you, main loop) | Fable 5 | Plan, spec, orchestrate, advise — answer workers' questions when they're stuck or need a product/technical direction call; final judgment on what ships |
| Workhorse | Codex gpt-5.6 Sol, medium effort | Bulk of code generation: features, refactors, migrations, token-hungry work |
| Fast worker | Codex gpt-5.6 Luna, high effort | Tightly scoped grunt work: quick edits, surveys, file ops, running checks, repo chores |
Never gpt-5.5. Delegate for scale and context isolation, not "smarter" thinking. Treat the Workhorse as a peer engineer: specs state the goal and the why, not step-by-step instructions.
1 — Spec
Triage first: trivial (<~30 lines, or faster to do than spec) → do it yourself and say why. Ambiguous scope that's the user's call → ask 1–3 concise questions first. Note git status so worker changes stay distinguishable; commit nothing unless asked.
Write the spec to <scratchpad>/spec.md as compact XML blocks:
<task>One concrete job: goal, repo context, key files.</task>
<scope>In: ... Out: ... (explicit — this is where scope creep dies)</scope>
<implementation_notes>Decisions already made; interfaces and patterns to conform to.</implementation_notes>
<acceptance_criteria>Numbered, testable.</acceptance_criteria>
<verification_loop>Exact commands to run before declaring done.</verification_loop>
<action_safety>Stay narrow. No unrelated refactors, no new deps unless specified, no commits.</action_safety>
<escalation_contract>If blocked, or facing a decision that changes architecture, scope, or
public interfaces — do NOT guess. Print a "QUESTIONS:" block with options considered, then stop.</escalation_contract>
<output_contract>End with: files touched, what was verified (commands + results), residual risks.</output_contract>
2 — Run Codex
Resolve the companion runtime (highest version under ~/.claude/plugins/cache/openai-codex/codex/, scripts/codex-companion.mjs), then:
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.
- 3d ago First seen · 59 lines · 57 tokens per session scan A 1bb50e7ebec3
delegate is a skill published in the GitHub repository ohong/agent-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 1,024 once invoked, about $0.0003 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…