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 intent-driven-dev/openspec-schemas --skill openspec-bulk-apply-changegit clone --depth 1 https://github.com/intent-driven-dev/openspec-schemasWrote 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/intent-driven-dev/openspec-schemas/openspec-bulk-apply-change)<a href="https://agentmods.dev/skills/intent-driven-dev/openspec-schemas/openspec-bulk-apply-change"><img src="https://agentmods.dev/badge/skills/intent-driven-dev/openspec-schemas/openspec-bulk-apply-change/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/intent-driven-dev/openspec-schemas/openspec-bulk-apply-change"><img src="https://agentmods.dev/badge/skills/intent-driven-dev/openspec-schemas/openspec-bulk-apply-change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 81 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00030 | $0.00693 |
| Opus 5.5 | $0.00012 | $0.00277 |
| Sonnet 5.5 | $0.00006 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
openspec-bulk-apply-change 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenSpec Bulk Apply
Apply multiple active OpenSpec changes by creating isolated worktrees, dispatching delegated apply flows in parallel subagents, running verification in each flow, and reporting back without merging.
When to Use
- More than one active OpenSpec change exists
/opsx-applywas invoked without an explicit change target- The user wants multiple changes applied in parallel
Do not use this skill when the user explicitly targeted one change for /opsx-apply.
Steps
-
Get candidate changes
Run
openspec list --jsonto get active changes.- If the command input included change names, limit analysis to those changes.
- If fewer than 2 active candidate changes remain, do not use bulk mode. Fall back to normal single-change apply.
-
Collect change context
For each candidate change:
- Run
openspec status --change "<name>" --json - Run
openspec instructions apply --change "<name>" --json - Read listed
contextFiles - Read the tasks artifact and summarize pending work
- Note the implementation scope needed by the delegated apply flow
- Run
-
Create isolated worktrees
For each candidate change:
- Create a git worktree under
.worktrees/<change> - Keep the parent agent out of direct implementation work in the main workspace
- Create a git worktree under
-
Dispatch subagents in parallel
For each candidate change:
- Dispatch one subagent in that change's worktree
- Run all delegated apply flows in parallel
- Do not apply any change directly in the parent agent
-
Require apply then verify in each subagent
Instruct each subagent to:
- run
/opsx-apply <change> - run
/opsx-verify <change>after apply work is complete - stop after verification
- summarize implementation outcome, verification status, changed files, blockers, and unresolved warnings
- run
-
Collect and normalize reports
For each executed change, capture:
- Worktree path
- Apply status (
complete,paused,failed) - Verify status (
ready,warnings,critical,failed) - Files changed summary
- Blockers or unresolved warnings
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 · 92 lines · 30 tokens per session scan A b77720e8cdda
openspec-bulk-apply-change is a skill published in the GitHub repository intent-driven-dev/openspec-schemas (110 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 693 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
gsd-quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.
gsd-complete-milestone
Archive completed milestone and prepare for next version.
gsd-quick-batch
Batch several /gsd-quick-shaped tasks together — planned, dispatched, and merged as one run.
gsd-workspace
Manage GSD workspaces — create, list, or remove isolated workspace environments.
gsd-inbox
Triage and review open GitHub issues and PRs against project templates and contribution guidelines.
gsd-pause-work
Create context handoff when pausing work mid-phase.