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 specifygit 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/specify)<a href="https://agentmods.dev/skills/kreek/consult/specify"><img src="https://agentmods.dev/badge/skills/kreek/consult/specify/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/specify"><img src="https://agentmods.dev/badge/skills/kreek/consult/specify.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 | $0.00028 | $0.01027 |
| Opus 5.5 | $0.00011 | $0.00411 |
| Sonnet 5.5 | $0.00006 | $0.00205 |
| Haiku 4.5 | $0.00003 | $0.00103 |
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 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 — 91 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
- Work that touches more than one contract, component, module boundary, state transition, or domain invariant.
- Adding or changing a public surface, shared structure, or a structural runtime dependency (framework, database, ORM, auth client, SDK, job queue).
- Significant new code with no caller-facing boundary: a substantial module, non-trivial logic, or a deliberate change to observable behavior.
- Ambiguous or risky intent, or the user asks for an ADR, RFC, tech spec, or design note.
When NOT to Use
- Typos, docs-only edits, internal helper extraction, private file moves, dependency bumps with no public surface change, or narrow bug fixes that restore intended behavior.
- The design is settled and the user wants a task plan; use
workflowor the host's planning mode. To file it as tracker work, useissue-tracking. - A caller-facing interface is already concrete and only needs approval; use
contract-first.
Rules
- Design-partner means the agent proposes concrete options and the human approves, revises, or rules them out. Neither "the agent decides alone" nor "the human should come up with the design" is this mode.
- Stay above implementation sequencing. Specify owns contracts, states, tradeoffs, risks, and decisions. File-by-file edits, pseudocode, and task checklists belong to planning after the direction is agreed.
- Contracts are any caller-facing boundary: function signature, module export, public type, error vocabulary, CLI flag, environment variable, schema or migration step, event payload, file format, config key. "API" does not mean only HTTP.
- A design written before reading code is speculation. Cite the current
surface with
file:lineevidence, or name the adjacent convention for greenfield work. - Ask the smallest question that changes the shape: one recommended option with its key tradeoff and approve/revise/rule-out, secondary uncertainties as notes. Open questions that block the design are asked now, not left for code review.
- When a design artifact lists interfaces or domain shapes, mark each one approved or proposed.
- Spikes are disposable: ask first, keep them local and small, discard or rewrite after convergence.
- Capture only what will be used, in the smallest useful form, in
checked-in
docs/when the team should keep it. Record what the user approved, not what was proposed.
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.
- 16d ago Changed · -1 tokens per session cb1719d3b4d8
- 23d ago Changed · -8 lines a75f77effea7
- 1mo ago Changed · -51 lines 6bb06e370556
- 1mo 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 17d ago), licensed MIT. It adds 28 tokens to every session and 1,027 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…