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/zts0hg/codexspec/blueprintgit clone --depth 1 https://github.com/Zts0hg/codexspecWrote 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/commands/zts0hg/codexspec/blueprint)<a href="https://agentmods.dev/commands/zts0hg/codexspec/blueprint"><img src="https://agentmods.dev/badge/commands/zts0hg/codexspec/blueprint.svg" alt="Measured on agentmods" 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 | $0.00011 | $0.01318 |
| Opus 5 | $0.00005 | $0.00659 |
| Sonnet 5 | $0.00002 | $0.00264 |
| Haiku 4.5 | $0.00001 | $0.00132 |
Grade A, and why
blueprint 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blueprint Requirements Discovery
Language Preference
Read .codexspec/config.yml. Two independent language controls apply (each falls back to
language.output, then English):
- Interaction language (
language.interaction): language for all conversation with the user. - Document language (
language.document): language for requirements Markdown sent to the helper.
Converse in the interaction language and author requirement content in the document language. Use clear, standard software-development terminology; do not invent abbreviations to summarize concepts.
User Input
$ARGUMENTS
Goal
Discuss and confirm one new requirement, or maintain one existing pending requirement, in the single
shared .codexspec/blueprint.md. This command never creates a feature directory, changes a
development status, or starts SDD development.
Shared Workspace
- Run
codexspec _blueprint-helper inspect --ensurefrom the invoking repository. - Use only the returned worktree and blueprint. Never read or edit a blueprint copy in the caller
checkout, and never write
.codexspec/blueprint.mddirectly. - Retain the returned
blueprint_hashfor one helper mutation request. - Read
.codexspec/memory/constitution.md, all constraints and relevant records under.codexspec/profile/, relevant implemented features under.codexspec/specs/, and every current blueprint block before discussing or changing a requirement.
Allowed Work
- Append one newly confirmed requirement as the last pending block.
- Replace the complete agent-authored Markdown of one pending block while preserving its Feature ID.
- Delete one pending block after explicit confirmation.
- Move one pending block to the first/last pending position or before/after another pending block.
- View
in_progressandcompletedblocks as context. Never modify, delete, or move them.
Blueprint order is implementation order. Resolve prerequisites and requested reordering here; do not add priorities, dependency metadata, or scheduling behavior.
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 · 129 lines · 11 tokens per session scan A a51c05fce7cb
blueprint is a command published in the GitHub repository Zts0hg/codexspec (5 stars, last pushed 4d ago), licensed MIT. It adds 11 tokens to every session and 1,318 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 2026-09-03.
Other commands, from other repositories
set-tracker
Set the issue tracker for the current project.
zh
切换 Claude Code 为简体中文（/chinese 的短别名）.
plan-start
5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.
fire-todos
Capture, list, and manage todos during work sessions.
fire-execute-plan
Execute a single plan with segment-based routing, per-task atomic commits, and test enforcement.
sddp-prd
Command description: Create or refine the canonical product document. Argument hint: [rough product idea, users, domain, or market opportunity] Command category: project-bootstrap Prerequisites: none.