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 agentmods add skills/kreek/consult/workflownpx skills add kreek/consult --skill workflowgit clone --depth 1 https://github.com/kreek/consultWhat 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 | $0.00031 | $0.02436 |
| Opus 5 | $0.00015 | $0.01218 |
| Sonnet 5 | $0.00006 | $0.00487 |
| Haiku 4.5 | $0.00003 | $0.00244 |
Grade A, and why
workflow 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 yesterday.
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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow
Iron Law
COMPLEXITY IS THE ENEMY: KEEP SOFTWARE SIMPLE ENOUGH TO UNDERSTAND, CHANGE, AND PROVE.
When to Use
- First, for almost every software engineering task when Consult skills are installed: feature work, bug fixes, scaffolding, refactoring, debugging, UI work, tests, docs, config, CI, dependencies, architecture, integrations, and read-only investigation whose answer will shape later engineering work.
When NOT to Use
- A narrower skill is explicitly requested and fully covers the task.
- The change is trivial, with no behavior, contract, data, security, or maintainability risk.
- The work is DevOps/platform operations with no software design, code, contract, or proof question.
Core Ideas
- Simple Made Easy is the Consult lens. Prefer designs that separate concerns, make state and effects explicit, and reduce what future maintainers must hold in their heads. Easy-to-type, familiar, or quick-to-generate is not the same as simple.
- The human must keep owning the system. Non-trivial work should leave the user with a clearer model of the system, the change, and the evidence. If you cannot explain your change clearly, stop and clarify.
- Consult owns the engineering standards; the host owns mechanics. Consult sets the bar for what counts as done; the host sets how the work happens. On conflict, clear the Consult bar inside the host's form.
- Default to the smallest honest solution. Implement only what was asked, prefer established tools, start with the happy path unless safety or data loss demands edge cases now, and add abstractions only after real semantic duplication appears.
- Compose over inherit. Build behavior from small data transformations and explicit interfaces; use inheritance only when a framework or interop boundary requires it.
- Don't repeat yourself. Each behavior gets one authoritative, well-named home that the rest of the system reuses. This targets duplicated intent, not code that merely looks similar.
- Adopt before build. Before writing code for a solved problem, audit the ecosystem; ground structural runtime choices in project sources or official sources, then ask before locking in a dependency. Adopt when a maintained library fits at acceptable weight and comprehension cost.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 170 lines · 31 tokens per session scan A 916fb58c8f6f
workflow is a skill published in the GitHub repository kreek/consult (1 stars, last pushed 6d ago), licensed MIT. It adds 31 tokens to every session and 2,436 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
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.