specify

specify is a command for Codex from sergeyklay/.agents. It costs 20 tokens per session (231 once invoked), scanned A, original, Apache-2.0.

An automated workflow for turning a software request into a reviewed implementation plan. It assesses the request, writes a specification, checks it, revises serious issues, and plans the work.

In plain words
What is it for?
Use it to clarify feature requests, produce project-grounded specifications, review and revise them, and create a detailed coding plan.
Why use it?
It removes the need to run and coordinate these specification steps separately. It also helps catch important problems before coding begins.

Command for Codex

Install

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.

agentmods
npx agentmods add commands/sergeyklay/.agents/specify
Clone the repo
git clone --depth 1 https://github.com/sergeyklay/.agents

Made for: Codex.

Wrote 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.

agentmods badge for specify

README.md
[![agentmods](https://agentmods.dev/badge/commands/sergeyklay/.agents/specify.svg)](https://agentmods.dev/commands/sergeyklay/.agents/specify)
Your own site
<a href="https://agentmods.dev/commands/sergeyklay/.agents/specify"><img src="https://agentmods.dev/badge/commands/sergeyklay/.agents/specify.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 231 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.00231
Opus 5 $0.00010 $0.00115
Sonnet 5 $0.00004 $0.00046
Haiku 4.5 $0.00002 $0.00023

Measured 4d ago against content hash 10147a55125b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

.agents/commands/specify.md · 16 lines

What it actually says

Your task is to run the complete specification pipeline for the request below.

The pipeline:

  1. Assesses the input - determines the route (tracker-driven, description-driven, review-driven, revise-driven, or plan-already-exists) and selects the appropriate skip path
  2. Specifies - delegates to the architect agent, which loads the writing-specs skill and grounds the spec in project context
  3. Reviews - delegates to the arch-review agent, which loads the review-spec skill and emits a machine-readable Subagent Return Line
  4. Revises if needed - severity-gated: Significant-only findings trigger one revision; Critical findings enter a Critical Resolution Loop with up to two re-review cycles, then halt if unresolved
  5. Plans - delegates to the planner agent, which loads the writing-plans skill and produces an atomic, layer-aware plan

Follow your protocol strictly. Do not skip any phase. Track progress with the todo list.

Changes

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.

  1. 4d ago First seen · 16 lines · 20 tokens per session scan A 10147a55125b

Subscribe to this mod's changes

specify is a command published in the GitHub repository sergeyklay/.agents (5 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 231 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.