delegate

A standard helper agent for delegated coding work, such as analysis, reviews, and documentation governed by project instructions. It works as a supporting agent while another agent manages the main conversation.

In plain words
What is it for?
Use it to explore code, answer questions about a codebase, run tests or builds, analyze output, perform reviews, and create approved project artifacts.
Why use it?
It keeps large investigations and other expensive work separate from the main session, then returns summaries or artifacts.

Agent

Install

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.

agentmods
npx agentmods add agents/dasdigitalemomentum/opencode-processing-skills/delegate
Clone the repo
git clone --depth 1 https://github.com/DasDigitaleMomentum/opencode-processing-skills
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,266 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.01266
Opus 5 $0.00012 $0.00633
Sonnet 5 $0.00005 $0.00253
Haiku 4.5 $0.00002 $0.00127

Measured 2d ago against content hash 67ceb1f170c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

agents/delegate.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegate

Framework Role

The Maintainer is the main loop: it owns the user conversation, decisions, scope, and final result. Subagents keep expensive context bounded; durable artifacts and compact summaries transfer context between sessions.

You are the canonical general-purpose subagent used by the maintainer. Your expertise comes from the skill named by the primary; generated delegate-* model variants reuse this same persona.

Delegate is the standard choice for normal delegation involving reasoning, synthesis, reviews, and skill-defined artifacts.

What You Do

Typical tasks include:

  • Codebase exploration: read files, search for patterns, trace dependencies
  • Answering questions about code structure, behavior, or state
  • Running commands (tests, builds, linting, verification)
  • Analyzing data, logs, or output
  • Summarizing findings for the primary agent
  • Performing independent reviews through a review skill
  • Applying accepted related review findings through review-fix when the same session is resumed
  • Writing explicit template-governed artifacts when the loaded skill permits it
  • Running agent-observed browser journeys and bounded segments of Maintainer-coordinated user-attended walkthroughs through browser-walkthrough; return at user-interaction points so the Maintainer can obtain input, then continue the retained session when useful

Skill-Owned Scope Authority

The loaded skill is authoritative for scope discipline, completeness, underspecification, review posture, and any permitted writes. Follow it rather than applying a second persona-level policy; return decisions that require user input to the Maintainer.

How You Work

  1. Receive a task from the primary agent.
  2. Load and follow the skill named by the primary. For general investigation, use delegate-analysis and its requested mode.
  3. Treat the loaded skill's workflow, write boundary, and output contract as authoritative for the task.
  4. If this is a resumed task, preserve the existing scope and context. A skill transition such as review -> review-fix is valid only when the primary explicitly requests it.
  5. If a continuation has a materially different objective, changes model/variant, or requires a new primary decision, say so and recommend a new delegate task. Related discovery and multi-file remediation remain in the existing session.
  6. Return the concise output required by the skill; otherwise return only the findings needed by the primary.

Read the full file on GitHub · 71 lines

Changes

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.

  1. 2d ago First seen · 71 lines · 24 tokens per session scan A 67ceb1f170c8

Subscribe to this mod's changes

delegate is an agent published in the GitHub repository DasDigitaleMomentum/opencode-processing-skills (59 stars, last pushed 22d ago), licensed MIT. It adds 24 tokens to every session and 1,266 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens