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 skills add The-Biomechanist/Windows-Dev-Agent --skill workflow-plangit clone --depth 1 https://github.com/The-Biomechanist/Windows-Dev-AgentWrote 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/skills/the-biomechanist/windows-dev-agent/workflow-plan)<a href="https://agentmods.dev/skills/the-biomechanist/windows-dev-agent/workflow-plan"><img src="https://agentmods.dev/badge/skills/the-biomechanist/windows-dev-agent/workflow-plan.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 | $0.00035 | $0.00572 |
| Opus 5 | $0.00017 | $0.00286 |
| Sonnet 5 | $0.00007 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
workflow-plan 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 7d 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 — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Plan
Use planning when it changes execution quality. A trivial read or obvious single action does not need a multi-phase ceremony.
Procedure
- Bind the task. State the requested outcome, exact project/host boundary, hard constraints, and observable success condition.
- Inspect discriminating state. Use
env_inspect,tool_discover, or project-local reads only for facts that can change the route. Preserve unknown/failed probes instead of treating them as missing. - Get the runtime scaffold. Call
workflow_planwith the task, relevant context, and the active project boundary. In Codex, pass the current session/project directory explicitly ascwd. - Resolve the route. Read
selection_statusbefore treating any candidate as chosen. Deterministic selection requires discriminating overlap with capability identity/tags; generic operation words or description-only similarity are not enough.selectedmeans one strongest semantically distinguished route is executable.ambiguousmeans equal strongest task evidence remains; tool availability is an execution prerequisite, not a semantic tie-breaker.matched_unavailablemeans the uniquely strongest semantic route lacks an available configured tool; do not silently fall through to a weaker match.no_matchmeans the scaffold lacks sufficient discriminating capability evidence and ordinary task reasoning must choose the path. Whenroute_discriminatoris present, use it to state the unresolved joint rather than inventing a selection. - State execution phases. For each consequential phase include the entry state actually required, concrete action/tool, safety class, observable exit condition, and rollback only when an explicit restore path exists. A scaffold whose route is unresolved is not executable merely because it contains an
executephase. - Execute under the active host permission boundary. The model constructs the concrete executing call; Claude Code or Codex then decides whether that same call is permitted. Do not add a second model-controlled confirmation field that claims the host already approved it.
- Verify before continuing. A phase that changes upstream state invalidates downstream assumptions that depended on it; re-evaluate those dependencies rather than blindly replaying the original plan.
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.
- 7d ago First seen · 26 lines · 35 tokens per session scan A 7de217616edf
workflow-plan is a skill published in the GitHub repository The-Biomechanist/Windows-Dev-Agent (0 stars, last pushed 7d ago), licensed MIT. It adds 35 tokens to every session and 572 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 2026-08-31.
Other skills, from other repositories
cost-efficiency-analyzer
Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…
executive-financial-briefing
Generates a concise executive-level financial briefing or summary suitable for a CEO, CFO, or board presentation. Use when the user asks for a summary, briefing, executive summary, board update, financial overview, financial health check, or "how is the business doing". Covers the full P&L picture in one page. Also…
multi-quarter-trend-analysis
Analyzes financial trends across multiple quarters by comparing P&L metrics over time. Use when the user wants to see trends, patterns, trajectories, or directional movement across 3 or more quarters. Also use for "how are we trending", "show me the trend", "track performance over time", "quarter over quarter…
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
sector-rotation
Identify which market sectors to overweight or underweight based on current macro conditions and sector performance data.