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 javded-itres/Holix --skill holix-sdd-applygit clone --depth 1 https://github.com/javded-itres/HolixWrote 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/javded-itres/holix/holix-sdd-apply)<a href="https://agentmods.dev/skills/javded-itres/holix/holix-sdd-apply"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/holix-sdd-apply/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/javded-itres/holix/holix-sdd-apply"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/holix-sdd-apply.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 | $0.00032 | $0.00659 |
| Opus 5 | $0.00016 | $0.00329 |
| Sonnet 5 | $0.00006 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
holix-sdd-apply 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
User says implement / apply / do the change after a proposal exists under openspec/changes/<id>/.
Mandatory pre-apply gate
Before any product code:
-
sdd_statuswithchange_id— must beapply_ready -
sdd_request_apply_mode— get the question -
Ask the user in chat (show the prompt):
- self — main agent does all tasks
- subagents — dispatch by assignee (
mainstays on main) - hybrid — strictly follow each assignee
-
Wait for the answer. Then
sdd_set_apply_modewithself|subagents|hybrid -
sdd_apply— only proceeds if mode is set; returns plan (task → executor).
For subagents/hybrid it auto-dispatches using the exact assignee fromtasks.md(e.g.coder-python).
If mode is missing, sdd_apply fails on purpose. Do not start coding.
Implement
- Follow the plan from
sdd_applyonly; respect delta specs - Mode self: you execute every task (ignore assignees; do not spawn subagents)
- Mode subagents / hybrid: trust auto-dispatch /
sdd_dispatchjob ids — they use tasks.md assignee (custom types). Same type →type-1,type-2, … in parallel. Dispatch budgetsmax_stepsfrom each task's size (xs/s/m). Thenwait_subagent_result; domaintasks yourself.
Successful subagent jobs auto-mark their task checkbox intasks.md— you do not needsdd_check_taskfor those. Still callsdd_check_taskfor main tasks and if auto-mark failed. - After each main task:
sdd_check_task - When all done: suggest archive (
holix-sdd-archive/sdd_archive) - If a sub-agent thrash-fails on a still-large task: split that task in
tasks.mdinto smaller XS/S items and re-dispatch — do not just raise max_steps
Do NOT
- Do not code before user chooses apply mode
- Do not invent tasks outside
tasks.md - Do not call
delegate_to_subagentwith built-incoderwhen assignee is a custom type (coder-python, …) — that ignores the user's agent - Do not archive until user agrees (unless they asked)
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 · 52 lines · 32 tokens per session scan A 7fc9c13e999d
holix-sdd-apply is a skill published in the GitHub repository javded-itres/Holix (14 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 659 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.
Other skills, from other repositories
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
mstar-conventions
A guide to Morning Star project folders, plan files, documentation boundaries, and Git branches. It explains where plans, specifications, iterations, knowledge, and project files belong.
mstar-routing-eval
A Chinese-language evaluation skill for checking whether software tasks are routed to the right agents and project checkpoints.
mstar-iteration
Use when starting, driving, resuming, or closing a Morning Star iteration, or running an autonomous Phase 1–5 loop — including without a slash command (e.g. 'start an iteration', 'drive the iteration', 'run an autonomous loop'). Manages Phase 1 (default interactive direction lock; opt-in autonomous), Autonomous…
mstar-compound-refresh
A knowledge-maintenance workflow for reviewing project knowledge documents, removing outdated material, merging overlaps, or creating a starter knowledge set from a codebase.
mstar-design-md
DESIGN.md design system specification for Morning Star projects. Create, audit, and maintain project-level design tokens (Colors, Typography, Spacing, Elevation, Motion, Shapes, Components, Voice & Content) using Vercel Geist as reference template. Three-level completeness checklist (MVP/Standard/Production) with…