commit-to-codecollection

A workflow for rendering a tested RunWhen task as a private Custom Discovery CodeCollection in a Git repository. It is the version-controlled alternative to committing an inline task directly to a workspace.

In plain words
What is it for?
Use it after successful task testing when publishing reusable code to a private repository or deploying a registry skill template.
Why use it?
It helps teams store reusable automation in Git while ensuring the task has been tested and the target platform and scope are confirmed first.

Skill for Claude CodeCodex

Part of the runwhen-platform plugin — 15 skills, 3 agents, 1 MCP server shipped together

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 skills/runwhen-contrib/runwhen-platform-mcp/commit-to-codecollection
Any agent
npx skills add runwhen-contrib/runwhen-platform-mcp --skill commit-to-codecollection
Clone the repo
git clone --depth 1 https://github.com/runwhen-contrib/runwhen-platform-mcp

Made for: Claude Code, Codex.

Or install runwhen-platform, the plugin that ships this one along with the rest of its 15 skills, 3 agents, 1 MCP server.

Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,459 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 $0.00130 $0.03459
Opus 5 $0.00065 $0.01729
Sonnet 5 $0.00026 $0.00692
Haiku 4.5 $0.00013 $0.00346

Measured 2d ago against content hash 59fd42c9c2ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-to-codecollection 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 2d 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.

skills/commit-to-codecollection/SKILL.md · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit to CodeCollection (GitOps)

Render a tested tool-builder task into the Custom Discovery CodeCollection layout documented at https://docs.runwhen.com/guides/custom-discovery-codecollection/

This is the GitOps alternative to commit_slx (which writes inline scripts into the workspace repo).

When to use each path

Goal Tool
Fast iteration in a dev workspace commit_slx
Version-controlled, reusable bundle in your git repo render_codecollection_skill
Deploy a registry Skill Template deploy_registry_codebundle

Prerequisites

  1. Task already tested via run_script_and_wait (same bar as commit_slx)
  2. get_workspace_context loaded before authoring
  3. Platform format confirmed with the user (see below)
  4. runwhen-local release with the matching platform indexer on the target runner
    • platform: runwhen → RW-1355 runwhen indexer
    • platform: kubernetes|azure|aws|gcp → that cloud indexer enabled in workspaceInfo.yaml

Choose output format (ask the user first)

Do not call render_codecollection_skill until the user confirms platform and scope.

  1. Call list_discovery_platforms() and present the two main paths:
User goal platform Typical scope
One health-check SLX for the whole workspace (MCP tool-builder) runwhen resource_types: [workspace]
One SLX per K8s namespace/deployment/CRD/etc. kubernetes e.g. [namespace], [deployment]
One SLX per Azure/AWS/GCP resource azure / aws / gcp CloudQuery table names from catalog
  1. Ask clarifying questions when ambiguous:

    • "Should this run once per workspace, or once per Kubernetes namespace/cluster/resource?"
    • "Which cloud account scope — individual resources, resource groups, or subscriptions?"
    • For Kubernetes: "Which namespace pattern or resource type should drive SLX creation?"
  2. Call list_indexed_resource_types(platform=<chosen>, search=<hint>) and only offer resource_types values returned by that tool (plus Kubernetes CRD plural.group[/version] syntax when the user names a CRD).

Read the full file on GitHub · 304 lines

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. 2d ago First seen · 304 lines · 130 tokens per session scan A 59fd42c9c2ba

Subscribe to this mod's changes

commit-to-codecollection is a skill published in the GitHub repository runwhen-contrib/runwhen-platform-mcp (1 stars, last pushed 19d ago), licensed Apache-2.0. It adds 130 tokens to every session and 3,459 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

xcodebuildmcp-structured-output-review

Use when reviewing XcodeBuildMCP structured output schema changes, schema versioning, manifest outputSchema metadata, and JSON fixture compatibility.

getsentry/XcodeBuildMCP · 37 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens

mcp-transport-contract-auditor

Route shaft-mcp transport-contract audits to the canonical playbook.

ShaftHQ/SHAFT_ENGINE · 22 tokens

create-operator

MUST READ before creating or moving any operator (createop, copyop, setopposition, or executepython builds). Required verification, canonical positioning recipe, and error-checking steps.

dylanroscover/Embody · 42 tokens

cortex-automate

Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…

cdeust/Cortex · 93 tokens