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/specifynpx skills add kreek/consult --skill specifygit 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 | $0.00029 | $0.01820 |
| Opus 5 | $0.00015 | $0.00910 |
| Sonnet 5 | $0.00006 | $0.00364 |
| Haiku 4.5 | $0.00003 | $0.00182 |
Grade A, and why
specify 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 2d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specify
Iron Law
DESIGN-PARTNER MODE: READ THE SYSTEM, DECIDE THE SHAPE TOGETHER, THEN RECORD WHAT WAS AGREED.
When to Use
- Feature work, refactors, migrations, or bug fixes that touch more than one contract, component, module boundary, state transition, or domain invariant.
- Adding or changing a public surface: function signature, exported type, endpoint, event/queue payload, CLI flag, environment variable, config key, file format, or database schema/migration step.
- Choosing shared project/package/module structure or a structural runtime dependency such as a framework, database, ORM, auth client, SDK, state library, or job queue.
- Ambiguous or risky implementation intent where the agent should turn fuzzy goals into an approved design direction before code lands.
- Significant new code with no caller-facing boundary: a substantial new module or component, new or rewritten non-trivial logic or an algorithm, or a deliberate change to observable behavior. Agree the plan or shape before implementing.
- The user asks to design, specify, draft an ADR/RFC/tech spec, or capture a design note.
workflowchooses the Design-partner mode because architecture, domain modeling, caller-facing interfaces, cross-boundary contracts, or multi-component choices need human participation.
When NOT to Use
- Typos, formatting, comment-only edits, or docs-only changes with no executable or contract effect.
- Internal helper extraction with no caller-visible boundary.
- Narrow bug fixes that restore intended behavior with no contract, state, data, or boundary change.
- Pure dependency bumps with no public surface change.
- Small local file moves or private implementation organization that does not establish a package/module boundary future work will depend on.
- The user wants a concrete task plan after the design is already settled; use workflow or the harness planning mode instead.
- A caller-facing interface is already concrete and only needs approval; use
contract-firstdirectly.
What ships with it
1 file 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.
- 2d ago First seen · 150 lines · 29 tokens per session scan A 981305e6dad1
specify is a skill published in the GitHub repository kreek/consult (1 stars, last pushed 7d ago), licensed MIT. It adds 29 tokens to every session and 1,820 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 skills, from other repositories
batch
Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.
notion
Notion API for creating and managing pages, databases, and blocks. Use when the user wants to create a Notion page, query a Notion database, update Notion properties, search Notion, add content to Notion, manage Notion blocks, or interact with Notion data sources and workspaces via the API.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
scaffold
Project-aware file generation. Reads existing codebase conventions (naming, structure, imports, exports, test patterns) then generates new files that match exactly. Wires generated files into the project's registration points.
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.
organize
Repository structure only: directory layout, file placement, naming conventions, and where-does-this-belong decisions. Detects the project's convention, audits files against it, and executes move plans with import-path updates. Never changes code inside files beyond the import updates a move forces; in-file…