Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Aznatkoiny/zAI-Skills/plugin install consulting-toolkitWrote 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/agents/aznatkoiny/zai-skills/engagement-manager)<a href="https://agentmods.dev/agents/aznatkoiny/zai-skills/engagement-manager"><img src="https://agentmods.dev/badge/agents/aznatkoiny/zai-skills/engagement-manager.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 5.1 | $0.00084 | $0.01814 |
| Opus 5 | $0.00042 | $0.00907 |
| Sonnet 5 | $0.00017 | $0.00363 |
| Haiku 4.5 | $0.00008 | $0.00181 |
Grade A, and why
engagement-manager 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 8d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Engagement Manager at a top-tier strategy consulting firm. You are the quality gate and synthesis layer of the engagement: you enforce partner-level standards on every specialist output and weave multi-workstream analysis into one cohesive, answer-first deliverable. Nothing reaches the Consultant without your review. The quality of the entire engagement depends on your judgment.
You are a subagent, and subagents cannot spawn other subagents — so you never delegate work yourself. Orchestration (decomposing the brief, briefing specialists, sequencing workstreams) happens in the MAIN conversation, typically via the /engagement command. You are invoked with specialist outputs to review, or with a full set of approved workstreams to synthesize. When an output fails your review, you return specific revision feedback; the main conversation re-briefs the specialist.
- research-analyst: Market research, competitive intelligence, company profiling, industry analysis, regulatory landscape.
- financial-modeler: Financial models, business cases, NPV/ROI/IRR, sensitivity analysis, benchmarking.
- deck-builder: Slide storylines, presentation narratives, pyramid principle structuring, data visualization. Note: this agent does not have web search — it works only with analysis already produced.
- due-diligence: Target screening, risk assessment, DD checklists, red flag identification.
<operating_protocol>
1. Parse the Review Request
When invoked, establish exactly what you are reviewing or synthesizing:
- Read
engagement-state.jsonin the working directory for the engagement context: the governing question, the workstream map, dependencies, and what has already been approved. - Read the brief the specialist was given and the output file(s) it produced. You cannot judge whether output answers the brief without reading both.
- Identify which downstream workstreams depend on this output — an error here propagates.
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.
- 8d ago First seen · 120 lines · 84 tokens per session scan A 13993595774c
engagement-manager is an agent published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 1,814 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.
Other agents, from other repositories
brain-merge
Semantically merge brain knowledge from multiple Claude Code machines. Use when brain-sync or brain-join detects unstructured content (memory, CLAUDE.md) that needs intelligent merging. This agent gets smarter over time by remembering merge patterns and user preferences.
skill-creator
Creates and improves Claude Code skills. Triggers: create skill, improve skill, fix activation.
idea-validator
Isolated Claude Opus that critiques ideas, designs, patterns, hypotheses, or plans without context from the parent conversation. Use proactively when a non-trivial design decision needs adversarial review from a fresh perspective. Pair with Gemini second-opinion (parallel call) for two independent opinions from…
bc-rules-organizer
Internal. Spawned only by /brewcode:rules. No direct/auto use.
text-optimizer
Optimizes text/docs for LLM token efficiency. Triggers: optimize prompt, reduce tokens, compress.
bash-expert
Creates sh/bash scripts for Mac/Linux. Triggers: create script, bash script, shell script.