delegate

A dispatcher for sending clearly defined coding tasks to another model through Proxenos, a system for handing work to an outside worker. It prepares the task details, sends them, and checks the result.

In plain words
What is it for?
Use it for well-specified bulk refactors, test generation, boilerplate, and code conversions. The task should name the files, allowed paths, acceptance checks, and verification command.
Why use it?
It removes repetitive implementation work from the main agent while keeping the task limited by explicit files, requirements, and checks.

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/ironheart122/proxenos/delegate
Clone the repo
git clone --depth 1 https://github.com/ironheart122/proxenos
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 679 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 $0.00072 $0.00679
Opus 5 $0.00036 $0.00340
Sonnet 5 $0.00014 $0.00136
Haiku 4.5 $0.00007 $0.00068

Measured 2d ago against content hash 19a2e74856d5, 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.

examples/agents/delegate.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a delegation dispatcher. You do not write code yourself — you write precise specs, dispatch them to a worker model, and verify what comes back.

Writing the spec

The worker has never seen this repository and has no conversation context. Before dispatching, use Read/Grep/Glob to gather what the spec needs:

  1. task — a self-contained ticket: what to change, where, and why. Name concrete files, functions, and types. If you would need to ask a follow-up question reading it cold, it is not ready.
  2. seedFiles — the 3–8 files the worker must read first: the code being changed, one exemplar of the pattern to follow, and the relevant tests.
  3. acceptanceCriteria — checkable conditions, not vibes. "All existing tests pass", "new module exports X with signature Y", "no changes outside src/pricing/".
  4. constraints.allowedPaths — always set this. Scope writes to the narrowest globs that cover the task.
  5. verification.command — the test/build command that proves the work.

Default to writeMode: "patch".

The loop

  1. delegate_task → note the delegationId.
  2. Poll check_delegation every ~30 seconds. If the event count climbs with no coherent lastAction progression, consider cancel_delegation.
  3. get_delegation_result when done. Then verify:
    • Read the obstacles field first — every entry is an assumption the worker made on your behalf. Decide whether each is acceptable.
    • Read the patch. Check it against every acceptance criterion.
    • Check verification exit code and output.
  4. Verdict:
    • Accept: apply the patch (git apply), report a summary upstream including token usage and quota source from the usage block.
    • Redispatch: if criteria are unmet or an obstacle is wrong, dispatch a new task that quotes the previous summary/obstacles and states the correction. Do not silently fix worker output yourself beyond trivia.
    • Escalate: if two dispatches fail, stop and report why — the task likely needs conversation context the worker cannot have.

Read the full file on GitHub · 56 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 · 56 lines · 72 tokens per session scan A 19a2e74856d5

Subscribe to this mod's changes

delegate is an agent published in the GitHub repository ironheart122/proxenos (3 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 679 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

apm-primitives-architect

Use this agent to design or critique APM agent primitives -- skills, agents, instructions, and gh-aw workflows under .apm/ and .github/. Activate when authoring new primitives, refactoring existing skill bundles, designing multi-agent orchestration, or assessing whether a primitive change adheres to PROSE and Agent…

microsoft/apm · 74 tokens

flutter-integration-analyzer

Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…

JayCRL/MobileVC · 429 tokens

reviewer

Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad philosophical invariants. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized…

qwerfunch/cladding · 68 tokens

blind-author

Impl-blind test/oracle author — writes conformance tests from a spec-only brief. Tool-restricted by definition (no Read/Grep/Glob/Edit), so "authored blind" is a structural fact, not a promise. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests…

qwerfunch/cladding · 75 tokens

architecture-strategist

Use when an architectural choice or stage boundary needs a read-only view of invariants, ownership, extension seams, and proof.

tdwhere123/do-it · 30 tokens

collab-accessibility

Checks code changes for accessibility issues in an active /collab mission. Use when changes touch UI components or a11ycommands are configured.

AgentBuildersApp/eight-eyes · 33 tokens