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/commands/aznatkoiny/zai-skills/engagement)<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/engagement"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/engagement.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 | $0.00022 | $0.01073 |
| Opus 5 | $0.00011 | $0.00536 |
| Sonnet 5 | $0.00004 | $0.00215 |
| Haiku 4.5 | $0.00002 | $0.00107 |
Grade A, and why
engagement 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are orchestrating a full consulting engagement from the main conversation. Subagents cannot spawn other subagents, so YOU own the orchestration: you decompose the brief, invoke each specialist subagent with a crisp brief, run the engagement-manager agent as the quality gate over every output, and drive the engagement to a synthesized recommendation.
Engagement brief: $ARGUMENTS
- Restate the brief as a precise governing question and 2-3 success criteria (what the client would accept as "done"). If there is genuine strategic ambiguity (e.g., "organic entry or acquisition-led entry?"), ask the Consultant before proceeding — do not ask about formatting.
2. Decompose into Workstreams
- Decompose the question into 3-6 MECE workstreams, each with a clear owner agent, objective, and deliverable path.
- Owners: research-analyst (market/competitive/company research), financial-modeler (models, business cases, NPV/ROI, sensitivities), due-diligence (target screening, risk assessment, red flags). Add a deck-builder workstream only if the Consultant asked for a presentation.
- Map dependencies: research typically feeds the model (TAM/growth inputs) and DD; the deck, if any, comes last. Note which workstreams can run in parallel.
3. Initialize State
- Write
engagement-state.jsonin the working directory, conforming to the schema at${CLAUDE_PLUGIN_ROOT}/templates/engagement-state.schema.json: engagement name, client, governing question, the workstream list (id, owner, status, inputs, deliverable path, findings summary), plus emptydecisionsandopen_risksarrays. - This file is the single source of truth. Update it as each phase completes — never rely on memory.
4. Execute Workstreams in Dependency Order
For each workstream, in dependency order (parallel where independent), invoke the owner agent as a subagent via the Task mechanism with a crisp brief:
WORKSTREAM: [id and name]
OBJECTIVE: [precise question this workstream must answer]
CONTEXT: [client background, strategic situation, constraints]
INPUTS AVAILABLE: [files and approved outputs from upstream workstreams]
OUTPUT FORMAT: [exact deliverable and file path, e.g. "markdown memo with executive summary at market-sizing-<topic>.md"]
QUALITY CRITERIA: [what "good" looks like for this task, e.g. "all quantitative claims sourced [Source, Date]"]
DOWNSTREAM: [which workstreams consume this output and what they need from it]
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 · 65 lines · 22 tokens per session scan A baabb89fadd0
engagement is a command published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,073 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 2026-08-31.
Other commands, from other repositories
strip
This is the task-based stripper, not the always-on prior: a deliberate cleanup pass you asked for. Apply the fp-minify doctrine to the target and remove or compress comments that don't earn their place.
conjure-config
Set, view, or remove conjure preferences. Asks questions to understand what you want, then writes plain-language instructions that conjure commands follow automatically.
setup
A command that creates a Korean-language CLAUDE.md project guide from a template. CLAUDE.md is a file containing instructions and project context for the Claude coding assistant.
dock-chat
Dock the full conversation to Telegram — drive Claude from your phone.
undock
Undock from Telegram — resume normal terminal replies and approvals.
dock-approvals
Route Claude Code permission prompts to Telegram — step away briefly.