What is holix-sdd-propose?

A workflow for proposing non-trivial product, API, data-schema, or feature changes as OpenSpec documents before coding. OpenSpec is a structured format for recording requirements, design decisions, tasks, and project-specific changes.

Use it when starting a substantial change, choosing the correct project specification folder, recording the team's understanding, and creating the required planning artifacts.

It helps clarify what is being built and ensures the proposal, design, requirements, and task list are prepared before implementation. It also supports workspaces containing several projects.

holix-sdd-propose — Skill for Claude Code by javded-itres

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.

Any agent

npx skills add javded-itres/Holix --skill holix-sdd-propose

Clone the repo

git clone --depth 1 https://github.com/javded-itres/Holix

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/javded-itres/holix/holix-sdd-propose/github.svg)](https://agentmods.dev/skills/javded-itres/holix/holix-sdd-propose)

Your own site

<a href="https://agentmods.dev/skills/javded-itres/holix/holix-sdd-propose"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/holix-sdd-propose/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/javded-itres/holix/holix-sdd-propose"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/holix-sdd-propose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,320 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00031	$0.02320
Opus 5	$0.00015	$0.01160
Sonnet 5	$0.00006	$0.00464
Haiku 4.5	$0.00003	$0.00232

Measured 10d ago against content hash 3d78b8e81331, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

holix-sdd-propose 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 10d 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.

core/skills/bundled/holix-sdd-propose/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to use

User wants a non-trivial feature, API, schema, or product change. Work starts with a specification, not code.

Language (Studio locale)

Match the user's Studio UI language (ru or en only):

Chat (questions, summaries, progress) — that language only
All SDD artifacts via sdd_write_artifact (proposal, design, specs, tasks) — that language only
sdd_update_understanding summary / questions — that language only
Do not mix languages; do not write specs in the other language
Structural OpenSpec markers may stay English (## ADDED Requirements, GIVEN/WHEN/THEN), but narrative text, requirement titles, scenarios, and task descriptions must be in the selected locale

If the Studio prompt states locale=ru or locale=en, treat that as authoritative.

Multi-project workspaces

A workspace may contain several projects, each with its own openspec/.

sdd_list_projects — pick the project path (empty string = workspace root)
Pass project=<path> to every subsequent sdd_* tool for that work

Workflow (propose)

sdd_status with project= — if not initialized → sdd_init with the same project=
sdd_list_specs + sdd_read_spec for relevant domains
sdd_list_changes — avoid duplicate open changes
sdd_create_change with slug id and request= (user request text)
Understanding gate (if enabled in user prefs — see create_change response).

Before any clarifying questions to the user, complete this order:
1. Existing SDD knowledge
  - sdd_list_specs + sdd_read_spec for relevant domains (openspec/specs/)
  - sdd_list_changes with include_archive=true
  - Read related archived change artifacts under openspec/changes/archive/ (proposal, specs, design, tasks) and any overlapping open changes
2. Project context / /init if needed
  - Read .holix/HOLIX.md (and project-local notes if any)
  - If missing, empty, or insufficient for this request/domain: run project onboarding equivalent to /init for the project path (scan layout + key files; update HOLIX.md via update_holix_section, or ask the user once to run /init <path> if you cannot write). Do not skip when the codebase is unknown.
3. Assess understanding
  - Call sdd_update_understanding with honest score (0–100) and summary of what you learned from main specs, archives, and HOLIX — before dumping questions at the user
4. Only then ask residual clarifying questions in chat
  - After each answer: sdd_update_understanding again with user_answer and updated score / questions
  - If score < threshold → keep clarifying (status clarifying)
  - If score ≥ threshold → status ready: offer proceed or more questions
  - If later answers drop score below threshold → new clarifying cycle
5. Only after user agrees to proceed: sdd_confirm_understanding
- Do not fill full proposal/specs/tasks until confirmed (or gate disabled/skipped)
- Do not open with a long questionnaire before steps 1–3
Fill artifacts via sdd_write_artifact only (not write_file / inventing paths):
- proposal → openspec/changes/<id>/proposal.md
- design → openspec/changes/<id>/design.md
- tasks → openspec/changes/<id>/tasks.md
- specs → openspec/changes/<id>/specs/<domain>/spec.md (pass domain= or omit)
- There is no openspec/changes/<id>/specs.md — do not read_file that path
- Prefer sdd_status(change_id=…) → artifact_paths before reading anything
- proposal content — Why / What / Impact
- specs content — delta with ## ADDED|MODIFIED|REMOVED Requirements and GIVEN/WHEN/THEN
- design content — approach + task→assignee table
- tasks content — checklist with assignees (see below)

Read the full file on GitHub · 185 lines

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.

10d ago First seen · 185 lines · 31 tokens per session scan A 3d78b8e81331

Subscribe to this mod's changes

holix-sdd-propose is a skill published in the GitHub repository javded-itres/Holix (14 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 2,320 once invoked, about $0.0002 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 2026-08-30.

Claude Code OpenSpec Planning agent-skills ai assistant hermes hermes-agent holix propose sdd specs

mnemosyne

Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.

mnemosyne-oss/mnemosyne · 22 tokens

hermes-tweet

Use Xquik in Hermes Agent for public X research, monitoring, thread summaries, creator discovery & approved actions. Not affiliated with X Corp. Use when the user requests X data or a named action. Trigger with "search X", "monitor X", "post tweet", or "X trends".

Xquik-dev/hermes-tweet · 65 tokens

openspec-schema-authoring

Create or customize OpenSpec workflow schemas in this repository using openspec schema init and openspec schema fork. Use when the user wants to add, fork, or validate a schema under openspec/schemas/.

intent-driven-dev/openspec-schemas · 52 tokens

vrc-monitor-agent

Use for VRChat friend queries (online status, who played with whom, activity timelines, online patterns) and VRChat social actions (boop, invite, join world, friend management, group operations, image uploads) via the vrc-monitor MCP server on port 8799.

ggg123124/vrchat-assistant · 62 tokens

mnemosyne-maintenance

Use when: upgrading Mnemosyne, diagnosing slow/hung consolidation (mnemosynesleep), fixing missing embeddings, or troubleshooting import/version mismatches.

AtlasOmnia/donna-starter · 40 tokens

review-workflow

A review workflow for GitHub pull requests and issues, including judging whether changes can be merged or an issue can be closed. It requires read-only review, REST API access, and testing changes in practice.

ggg123124/vrchat-assistant · 46 tokens