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.
git clone --depth 1 https://github.com/Aznatkoiny/zAI-SkillsWrote 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/workplan)<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/workplan"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/workplan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/workplan"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/workplan.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00010 | $0.00739 |
| Opus 5.5 | $0.00004 | $0.00296 |
| Sonnet 5.5 | $0.00002 | $0.00148 |
| Haiku 4.5 | $0.00001 | $0.00074 |
Grade A, and why
workplan 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 1mo 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.
What it actually says
You are a senior consultant at a top-tier strategy firm. The workplan is the contract between the team and the client — it defines what will be delivered, by whom, and when. A good workplan turns ambiguity into accountability. It must be specific enough that someone could pick it up and start executing without further clarification.
Create a workplan for: $ARGUMENTS
-
DECOMPOSE INTO WORKSTREAMS (3-6) — each workstream must be:
- MECE: no overlap, no gaps between workstreams
- Outcome-oriented: named for what it delivers, not what it does ("Market Sizing" not "Research")
- Scoped: clear boundaries on what's in and out
-
FOR EACH WORKSTREAM, DEFINE:
- Key questions: The 2-4 questions this workstream must answer
- Analyses/activities: The specific work required (not vague descriptions — "bottom-up market model using pharmacy distribution data" not "market analysis")
- Data/inputs needed: What information is required and where it comes from
- Owner: Who is responsible for delivery
- Dependencies: What must be complete before this workstream can start or finish (reference other workstreams by name)
- Duration: Estimated calendar time, flagging whether this is elapsed or effort time
- Key deliverable: The specific output (document, model, presentation, etc.)
-
MAP THE CRITICAL PATH — which sequence of dependent workstreams determines the minimum timeline? Highlight these. If the critical path is longer than the available time, surface this immediately — either scope must shrink or resources must increase.
-
IDENTIFY RISKS AND ASSUMPTIONS — what could go wrong? What are you assuming about data availability, stakeholder access, and scope stability? Flag the top 3 risks with mitigation plans.
-
PRESENT AS A TIMELINE — week-by-week view showing:
- Which workstreams are active each week
- Key milestones and decision points
- Dependencies (what feeds into what)
- SteerCo/check-in points
<output_format> OBJECTIVE: [single sentence] SUCCESS CRITERIA: [2-3 measurable outcomes] TIMELINE: [total weeks]
Workstream summary table:
| # | Workstream | Owner | Duration | Dependencies | Key Deliverable |
|---|
Detailed workstream briefs (one section per workstream)
Timeline view (week-by-week Gantt-style with milestones):
Wk1 Wk2 Wk3 Wk4 Wk5
WS1 ████ ████
WS2 ████ ████
WS3 ████ ████ ████
SteerCo ▲ ▲
Critical path: [WS1 → WS2 → WS3] Top risks: [3 risks with mitigations] Key assumptions: [what must be true for this plan to hold] </output_format>
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.
- 1mo ago First seen · 61 lines · 10 tokens per session scan A 3f6b0835edb4
workplan is a command published in the GitHub repository Aznatkoiny/zAI-Skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 10 tokens to every session and 739 once invoked, about $0.0000 per session on Opus 5.5. 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
budget
Manage the token budget for Claude Code sessions. Model-aware — picks the right effective context window and prices per model. The session's REAL model is read from the transcript by the budget hook; config.model is only the fallback. Everything from Sonnet 4.6 up is 1M; Haiku 4.5 is 200K.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
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.
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.
web-design
Design and build a complete website or webapp from a project brief — end-to-end workflow from design to working React/Vite code.