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 skills/tsmztech/claude-code-plugins/apex-executenpx skills add tsmztech/claude-code-plugins --skill apex-executegit clone --depth 1 https://github.com/tsmztech/claude-code-pluginsWhat 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 | $0.00087 | $0.02274 |
| Opus 5 | $0.00044 | $0.01137 |
| Sonnet 5 | $0.00017 | $0.00455 |
| Haiku 4.5 | $0.00009 | $0.00227 |
Grade A, and why
apex-execute 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.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute Anonymous Apex
Execute Anonymous Apex code against a connected Salesforce org. This skill is user-invoked only — Claude constructs the Apex code based on what the user wants to accomplish, then executes it via the Salesforce CLI.
Prerequisites
You must be authenticated to a Salesforce org before executing Apex. If not authenticated, run the authentication script first.
Authentication
If the user is not authenticated or gets an auth error, run the authentication script:
node ${CLAUDE_PLUGIN_ROOT}/scripts/sf-auth.js --status
To authenticate interactively (opens browser):
node ${CLAUDE_PLUGIN_ROOT}/scripts/sf-auth.js --alias <alias>
To authenticate to a sandbox:
node ${CLAUDE_PLUGIN_ROOT}/scripts/sf-auth.js --alias <alias> --instance-url https://test.salesforce.com
CRITICAL: Safety Rules for DML Operations
Before executing ANY generated Apex code, you MUST analyze it for data-modifying operations.
DML Detection
Scan the generated code for these keywords (case-insensitive):
DML Statements: insert, update, delete, upsert, undelete, merge
Database Methods: Database.insert, Database.update, Database.delete, Database.upsert, Database.undelete, Database.merge, Database.emptyRecycleBin, Database.convertLead
Other Mutating Operations: System.enqueueJob, System.schedule, System.scheduleBatch, EventBus.publish, Messaging.sendEmail
If DML is Detected
- WARN the user that the code will modify data
- SHOW the complete Apex code that will be executed
- DESCRIBE exactly what will happen (e.g., "This will update the Rating field to 'Cold' on up to 10 Account records where Rating is currently null")
- ASK for explicit confirmation before executing
- Only proceed if the user confirms
If Code is Read-Only
If the code only contains queries ([SELECT ...]), System.debug(), Schema.describe*, Limits.*, or other non-mutating operations — execute without extra confirmation.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 213 lines · 87 tokens per session scan A 155c9bd8a17a
apex-execute is a skill published in the GitHub repository tsmztech/claude-code-plugins (2 stars, last pushed 6mo ago), licensed MIT. It adds 87 tokens to every session and 2,274 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…