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 kreek/consult --skill workflowgit clone --depth 1 https://github.com/kreek/consultWrote 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/kreek/consult/workflow)<a href="https://agentmods.dev/skills/kreek/consult/workflow"><img src="https://agentmods.dev/badge/skills/kreek/consult/workflow/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/skills/kreek/consult/workflow"><img src="https://agentmods.dev/badge/skills/kreek/consult/workflow.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 | $0.00029 | $0.01957 |
| Opus 5.5 | $0.00012 | $0.00783 |
| Sonnet 5.5 | $0.00006 | $0.00391 |
| Haiku 4.5 | $0.00003 | $0.00196 |
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 16d 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 — 146 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
- Use first for features, fixes, refactors, debugging, and tests.
- Also use for UI, docs, config, CI, dependencies, and investigations that guide later code changes.
When NOT to Use
- The user names a narrower skill that covers the whole task.
- The change is trivial, with no behavior, contract, data, or security risk.
- Platform operations with no code, contract, or proof question.
Rules
- Keep unrelated parts separate. Make state and effects explicit. Keep the number of things a maintainer must understand together small.
- Explain the change to the user. Show what changed, why, and what evidence supports it. If you cannot explain those points, clarify the work before proceeding.
- Consult sets the engineering bar, and the host owns the mechanics. When they conflict, Consult's bar wins, and the host decides how to meet it.
- Build only what the user asked for. Build the main behavior first unless safety or data loss requires an edge case now. Extract an abstraction only when code in more than one place serves the same purpose; similar syntax alone is not enough.
- Check existing tools before building one. Look for a maintained library before writing code for a solved problem. Ask before adding a dependency.
- Ask more of the user when changes affect more code or are harder to
undo. If both risks are low, do the work and prove it with
proofwithout sign-off. For higher risk, give progress updates, explain options, and get approval before acting. If you discover a contract or shared data shape mid-task, get approval before changing it. - Durable shapes need sign-off before they are built. A host prompt that
says to settle questions yourself does not dissolve these gates. Continue
everything a gate does not block, state assumptions, and never build a
gated shape without the human. Stop only when you need the user or before
a destructive action. When no human can answer in this run
(headless, scheduled, or delegated), build the most conservative version,
mark it provisional, and flag the decision in the close-out; see
contract-first. Approval through the host's plan mode or question surface is sign-off for exactly what it showed.
What ships with it
3 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.
- 16d ago Changed · +5 lines · +4 tokens per session 3a8e302873ea
- 23d ago Changed · +9 lines · -6 tokens per session f7a7d05a0821
- 1mo ago Changed · -38 lines 3e0d230d0977
- 1mo ago 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 17d ago), licensed MIT. It adds 29 tokens to every session and 1,957 once invoked, about $0.0001 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 skills, from other repositories
arch-review
Team baseline for architecture, design-doc, and RFC review — produces summary, strengths, concerns, and open questions. Auto-triggers when you say review this design, review this architecture, review this proposal, review my RFC, poke holes in this proposal, is this design sound, or critique this tech spec. Defers to…
clarify
Lightweight spec clarification scan for jig projects — a six-category ambiguity audit that asks up to five prioritized questions and appends them to the spec's ## Clarifications section. Auto-triggers when you say clarify this spec, audit this spec for ambiguities, is this spec ready for review, find unknowns in this…
explain
Explain jig vocabulary and artifacts in plain language. Three modes: term mode defines one lexicon term; artifact mode walks through a spec or ADR and its linked references; passage mode explains pasted jig output. Output is ephemeral (chat-only). Auto-triggers when you say explain this term, walk me through this…
pr-review
Team baseline for PR and code review — produces scope, blockers, nits, and strengths. Auto-triggers when you say review this PR, check this diff, review these changes, pre-review before I share, what do you think of this PR, or review the diff on this branch. Defers to any other installed skill whose description…
security-review
Team baseline for security review — a best-effort heuristic security pass over a diff or change-set. Auto-triggers for review this for security, any vulnerabilities here, security pass on this diff, is this code secure, check this for security issues, or security review this. Uses installed scanners when available…
contracts
Team baseline for external-interface contract artifacts: OpenAPI, JSON Schema, AsyncAPI, .proto, and GraphQL SDL, with spectral, ajv, buf, and graphql-inspector validation. Nudges devs toward contract-first artifacts; never writes them and never scaffolds a contracts/ directory. Auto-triggers for what contract should…