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/usejunior/safe-docx/openspec-applygit clone --depth 1 https://github.com/UseJunior/safe-docxWhat 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 | $0.00018 | $0.00296 |
| Opus 5 | $0.00009 | $0.00148 |
| Sonnet 5 | $0.00004 | $0.00059 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
/openspec-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 yesterday.
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.
This is a copy
89% identical to OpenSpec: Apply — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Guardrails
- Favor straightforward, minimal implementations first and add complexity only when it is requested or clearly required.
- Keep changes tightly scoped to the requested outcome.
- Refer to
openspec/AGENTS.md(located inside theopenspec/directory—runls openspecoropenspec updateif you don't see it) if you need additional OpenSpec conventions or clarifications.
Steps Track these steps as TODOs and complete them one by one.
- Read
changes/<id>/proposal.md,design.md(if present), andtasks.mdto confirm scope and acceptance criteria. - Work through tasks sequentially, keeping edits minimal and focused on the requested change.
- Confirm completion before updating statuses—make sure every item in
tasks.mdis finished. - Update the checklist after all work is done so each task is marked
- [x]and reflects reality. - Reference
openspec listoropenspec show <item>when additional context is required.
Reference
- Use
openspec show <id> --json --deltas-onlyif you need additional context from the proposal while implementing.
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.
- yesterday First seen · 24 lines · 18 tokens per session scan A f34f3fd92a98
/openspec-apply is a command published in the GitHub repository UseJunior/safe-docx (40 stars, last pushed 3d ago), licensed Apache-2.0. It adds 18 tokens to every session and 296 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to OpenSpec: Apply, differing in 6 lines, and is treated as a copy.
Other commands, from other repositories
doc-refactor
Refactor documents — simplify without losing information, visualize flows with sequenceDiagram.
bug-check
Run automated tests and build checks first, then agent code review. For each bug found, propose or document a regression test.
create-release
Cut a new release of a project or plugin — resolve release config, bump version(s), update CHANGELOG, create release PR, and tag.
status
Check Nowledge Mem connection and server status.
debug
用 Agent 工具啟動 debugger agent，把錯誤資訊原文（含截圖/log）完整轉給它。.
overview
專案鳥瞰——Scout 出敘事型 overview（分層架構＋模組職責＋依賴方向＋關鍵流程走讀）。唯讀、不落檔，每次都是現況。.