agentmods.dev

opsx-bulk-apply

A command for applying several OpenSpec changes at the same time in separate Git worktrees. A worktree is an isolated working copy of a repository, so changes can be handled independently.

In plain words
What is it for?
Use it for two or more active OpenSpec changes that should each be applied, verified, and reported without being merged or archived automatically.
Why use it?
It keeps concurrent changes from interfering with one another while each is implemented and checked.

Command

121 8d ago A scan 10 tokens original MIT
View the source file intent-driven-dev/intent-driven-template
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.

agentmods
npx agentmods add commands/intent-driven-dev/intent-driven-template/opsx-bulk-apply
Clone the repo
git clone --depth 1 https://github.com/intent-driven-dev/intent-driven-template
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 445 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.00445
Opus 5 $0.00005 $0.00222
Sonnet 5 $0.00002 $0.00089
Haiku 4.5 $0.00001 $0.00044

Measured yesterday against content hash 781561c109a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.opencode/commands/opsx-bulk-apply.md · 67 lines

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

  1. Get candidate changes

    Run:

    openspec list --json

    If change names were provided, limit candidates to those names.

  2. 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.

  3. 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-apply behavior.
  • 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.
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.

  1. yesterday First seen · 67 lines · 10 tokens per session scan A 781561c109a7

Subscribe to this mod's changes

opsx-bulk-apply is a command published in the GitHub repository intent-driven-dev/intent-driven-template (121 stars, last pushed 8d ago), licensed MIT. It adds 10 tokens to every session and 445 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 2026-08-30.

Git and workflowOpenSpecPlanningWriting and docsarchitectural-decision-recordsc4modelcontext-engineeringgit-worktreesopencode
Related

Other commands, from other repositories

OpenSpec: Proposal

Scaffold a new OpenSpec change and validate strictly.

puppyone-ai/puppyone · 16 tokens

OpenSpec: Archive

Archive a deployed OpenSpec change and update specs.

puppyone-ai/puppyone · 15 tokens

OpenSpec: Apply

Implement an approved OpenSpec change and keep tasks in sync.

puppyone-ai/puppyone · 17 tokens

sample-command

A sample command for testing.

rp1-run/rp1 · 8 tokens

ctx:git-commit

Deterministic commit and push workflow using scripts (DRY compliant).

shakestzd/contextune · 20 tokens

ctx:research

Fast research using 3 parallel Haiku agents for technical questions and decision-making (1-2 min).

shakestzd/contextune · 25 tokens