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.
git clone --depth 1 https://github.com/intent-driven-dev/intent-driven-templateWrote 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/intent-driven-dev/intent-driven-template/opsx-bulk-apply)<a href="https://agentmods.dev/commands/intent-driven-dev/intent-driven-template/opsx-bulk-apply"><img src="https://agentmods.dev/badge/commands/intent-driven-dev/intent-driven-template/opsx-bulk-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/commands/intent-driven-dev/intent-driven-template/opsx-bulk-apply"><img src="https://agentmods.dev/badge/commands/intent-driven-dev/intent-driven-template/opsx-bulk-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 | $0.00010 | $0.00445 |
| Opus 5.5 | $0.00004 | $0.00178 |
| Sonnet 5.5 | $0.00002 | $0.00089 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
opsx-bulk-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 1mo 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.
What it actually says
Apply multiple active OpenSpec changes concurrently.
Input: Optionally specify two or more change names (e.g., /opsx-bulk-apply add-auth improve-search). If omitted, discover active changes with openspec list --json.
Required skill: Use openspec-bulk-apply-change.
Steps
-
Get candidate changes
Run:
openspec list --jsonIf change names were provided, limit candidates to those names.
-
Check candidate count
- If fewer than 2 active candidate changes remain, stop and tell the user to use
/opsx-apply <change>. - If 2 or more candidates remain, continue with
openspec-bulk-apply-change.
- If fewer than 2 active candidate changes remain, stop and tell the user to use
-
Follow the bulk apply skill exactly
The skill must:
- Run OpenSpec git discipline checks before apply.
- Create isolated worktrees under
.worktrees/<change>unless another root is requested. - Dispatch one subagent per change.
- Run
/opsx-apply <change>and/opsx-verify <change>in each subagent. - Collect normalized apply and verify reports.
- Report results without merging or archiving.
Output
## Bulk Apply Report
### Changes Analyzed
- <change>
### Worktrees
- `<path>`
### Results
| Change | Apply | Verify | Review Ready |
| --- | --- | --- | --- |
| <change> | complete | ready | yes |
### Blockers and Warnings
- <change>: <details>
No merge or archive was performed. Explicit user approval is required before any merge or archive.
Guardrails
- Do not modify existing single-change
/opsx-applybehavior. - Do not ask the user to choose one change when the request is clearly bulk apply and 2 or more candidates exist.
- Do not apply changes directly in the parent workspace.
- Do not merge, archive, or commit unless the user explicitly asks for that follow-up action.
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.
- 1mo ago First seen · 67 lines · 10 tokens per session scan A 781561c109a7
opsx-bulk-apply is a command published in the GitHub repository intent-driven-dev/intent-driven-template (169 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 445 once invoked, about $0.0000 per session on Opus 5.5. 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 commands, from other repositories
release
Verify, write the CHANGELOG, cut a version — then hand the release sequence back.
OPSX: Archive
Archive a completed change in the experimental workflow.
project
Manage projects: register repos, inspect, configure per-project settings, and remove.
commit-push-pr
Commit, push, and open a PR.
commit
Run when user calls /commit or asks to generate a commit message. Analyzes staged changes and writes a structured commit message.
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.