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 commands/chappygo-os/atomic-spec/specifygit clone --depth 1 https://github.com/Chappygo-OS/Atomic-SpecWhat 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 | $0.00013 | $0.04419 |
| Opus 5 | $0.00006 | $0.02210 |
| Sonnet 5 | $0.00003 | $0.00884 |
| Haiku 4.5 | $0.00001 | $0.00442 |
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 — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Outline
The text the user typed after /atomicspec.specify in the triggering message is the feature description. Assume you always have it available in this conversation even if {ARGS} appears literally below. Do not ask the user to repeat it unless they provided an empty command.
Given that feature description, do this:
-
Platform Detection (CRITICAL - runs BEFORE all other steps):
Platform context is essential for mobile apps and must be established first.
a. Check registry for existing platform: Read
specs/_defaults/registry.yamland check fortarget_platform.primaryb. If platform is found in registry:
- Use that value as the Platform for this spec
- Inform user: "Using platform from project defaults: [platform]"
c. If platform is NOT found in registry:
- Ask user with AskUserQuestion:
What platform are you building for? - Web (browser-based application) - iOS (native iPhone/iPad app) - Android (native Android app) - React Native (cross-platform mobile) - Flutter (cross-platform mobile) - Mobile + Backend (mobile app with dedicated backend/API) - Backend-only (API / service with no user-facing frontend) - If user selects "Mobile + Backend":
- Ask a follow-up AskUserQuestion:
Which mobile framework will you use? - React Native - Flutter - iOS (native Swift/SwiftUI) - Android (native Kotlin/Compose) - Store the mobile framework choice in
specs/_defaults/registry.yamlundermobile_framework - Set the Platform value to
both(the registry'smobile_frameworkandbackend.*fields provide the specifics)
- Ask a follow-up AskUserQuestion:
- If user selects "Backend-only":
- Set the Platform value to
Backend-only
- Set the Platform value to
- Store the user's response for use in step 5
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 · 391 lines · 13 tokens per session scan A 5a75f318781a
specify is a command published in the GitHub repository Chappygo-OS/Atomic-Spec (10 stars, last pushed 9d ago), licensed MIT. It adds 13 tokens to every session and 4,419 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 commands, from other repositories
assistant
Single entry point of the Claude Code foundation. Guides toward the right commands, agents, skills and workflows.
constitution
根据交互输入或已提供原则创建或更新项目章程，并确保相关模板保持同步。.
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
ijfw-execute
Jump directly to the IJFW workflow Execute phase (Deep D4 / Quick Q3). Usage: /ijfw-execute [task or phase name].
ijfw-metrics
Show IJFW token / cost / session metrics over a time window. Reads .ijfw/metrics/sessions.jsonl via the ijfwmetrics MCP tool.
core-review
Review code changes against SpecOps project-specific patterns. Catches recurring failure modes from real PRs — tool abstraction violations, generated file drift, cross-platform gaps, variable inconsistencies, and more. Complements full-review-gate (generic quality) and pr-fix (applying bot comments).