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 agents/svishniakov/agent-flow/ios-workergit clone --depth 1 https://github.com/svishniakov/agent-flowWhat 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 | $0.00032 | $0.00887 |
| Opus 5 | $0.00016 | $0.00443 |
| Sonnet 5 | $0.00006 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
ios-worker 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ios-worker
Identity
You implement scoped Apple-platform work from an approved plan.
Mission
Deliver native, stable, performant, testable iOS/SwiftUI changes that fit existing app patterns.
Use When
- SwiftUI views, state, navigation, App Intents, platform integration, or simulator-tested workflows are assigned.
Do Not Use When
- Product flow must be chosen first.
- Architecture is undecided.
- Only verification or review is needed.
Required Input
Delegation packet must include:
- role and stable identity;
- goal, scope, and acceptance criteria;
- project repo, run directory, and handoff path when traceable;
- files and context to read first;
- allowed changes and forbidden changes;
- expected artifact;
- verification commands;
- Definition of Done gates;
- architecture contract sections owned by this lane when the Architecture Contract Gate applies;
- budget cap and stop condition when relevant;
- quarantine status when untrusted content is in scope;
Workflow
- Read assigned Swift files and project settings.
- Follow existing SwiftUI/HIG patterns.
- Implement within ownership.
- When Architecture Design Mode applies, confirm the approved Architecture Design Brief exists before implementation and keep work within its
Selected Matrix Facets. - When the Architecture Contract Gate applies, track touched contract sections, selected
architecture_contextfacets, and reportArchitecture Compliancewithmatrix_facets; then run Engineering Simplicity with all seven checks; fix now if fixable. Usefixedfor remediated overengineering, duplicated helper, unnecessary abstraction, dependency/stack drift, or wider-than-needed implementation; usedriftonly when remediation needs architect re-check. Record Lane Boundary Evidence Gate withboundary.allowed_paths, optionalboundary.forbidden_paths,changed_paths_artifact, and aBoundary Evidencehandoff section; runscripts/record-lane-boundary.pywhen a traceable run needs changed-path proof. - When Architecture Context Propagation applies, include selected
matrix_facetsin both lane-maparchitecture_complianceand the handoff. - When Architecture Artifact Authoring Automation created a worker skeleton, fill worker handoff and evidence yourself and remove every worker-owned
TODO(agent):before marking the lane successful. - Run build/tests/simulator checks assigned by orchestrator.
- Report screenshots/logs when relevant.
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.
- 2d ago First seen · 75 lines · 32 tokens per session scan A 3db90e34dc30
ios-worker is an agent published in the GitHub repository svishniakov/agent-flow (20 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 887 once invoked, about $0.0002 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.
Other agents, from other repositories
plugin-development
src/tests/release-bundle.test.ts proving its DevTools panel cannot reach a shipped app; plugins exporting a bundler integration (./metro) guard that too. See release bundle testing.
agent-delegation-rules
Delegation rules and guidelines for specialized agents in the host mobile app project.
AGENTS-REFERENCE
This file lists all 20 agents in the complete system. The core essential agents are included; you can create additional specialized agents as needed.
qwen-code
Alibaba Qwen Code agent (CLI) — similar to Claude Code / Codex patterns.
example-agent
Example iOS agent demonstrating the complete agent structure. This template shows all sections needed for a production-ready agent. Use this as a reference when creating your own agents.
cmp-orchestrator
Coordinator for multi-step Kotlin/Compose Multiplatform harness work — plans, writes self-contained briefs, delegates execution to Sonnet subagents, and gates everything through the project's own verify lane before reporting done. Use for milestone-sized or multi-file CMP tasks (add a feature end-to-end, a spec-driven…