sync-agents

A command that updates four project-local agent configuration files so they match the installed SoloFlow version and retain access to required MCP tools. MCP tools are external tool connections used by agents.

In plain words
What is it for?
Use it after updating SoloFlow, or when a sprint preflight reports drift, to refresh the agent files in `.claude/agents/`.
Why use it?
It fixes configuration drift after plugin updates and prevents project agents from using outdated definitions or missing tool access.

Command

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 commands/kesteva/soloflow/sync-agents
Clone the repo
git clone --depth 1 https://github.com/kesteva/soloflow
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 995 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 $0.00018 $0.00995
Opus 5 $0.00009 $0.00498
Sonnet 5 $0.00004 $0.00199
Haiku 4.5 $0.00002 $0.00100

Measured 2d ago against content hash 67633d302e53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync-agents 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.

commands/sync-agents.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/soloflow:sync-agents

Updates the four MCP-dependent agent shadows in .claude/agents/ to match the current SoloFlow plugin version. Use this after a plugin update (or whenever /soloflow:sprint's preflight warns about drift).

Why these shadows exist. Plugin-scoped subagents silently ignore the mcpServers: frontmatter key, so a plugin-scoped verifier would never receive Maestro/Playwright/context7 bindings. Project-local copies in .claude/agents/ DO honor the declaration. To ensure no competing plugin-scoped shadow-verifier (etc.) overrides the project-local copy, the templates live at {plugin_root}/agent-templates/ — outside the plugin's auto-discovered agents/ directory. The plugin therefore exposes zero shadow-* agents of its own; the only ones the harness sees are the ones this command writes into .claude/agents/. Each shadow's tools: array also explicitly lists its MCP tool bindings (e.g. mcp__maestro__*, mcp__playwright__*, mcp__context7__*) — Claude Code treats tools: as a strict allowlist, so mcpServers: alone does not grant tool access. Each shadow carries its own version stamp as a YAML comment at the top of the frontmatter (# soloflow-shadow: version=X synced=Y) — invisible to Claude Code's YAML parser and to the LLM, but readable by this utility's drift check.

Note: the Maestro entry in the visual verifier shadows only governs the MCP path. Mobile visual verification also has a CLI fallback (via Bash), so stale Maestro shadows silently degrade to CLI mode rather than skipped_unable. Playwright has no CLI fallback.

Managed agents

Agent Declares Used by
shadow-verifier.md mcpServers: [maestro, playwright] per-task Level 2 visual verification
shadow-sprint-verifier.md mcpServers: [maestro, playwright] end-of-sprint visual check
shadow-researcher.md mcpServers: [context7] idea research
shadow-roadmap-researcher.md mcpServers: [context7] roadmap research

Read the full file on GitHub · 55 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 · 55 lines · 18 tokens per session scan A 67633d302e53

Subscribe to this mod's changes

sync-agents is a command published in the GitHub repository kesteva/soloflow (41 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 995 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.