what-iff: Skill for Claude Code

.claude/skills/ci-local/SKILL.md

ci-local is a skill for Claude Code from theimaginaryfoundation/what-iff. It costs 74 tokens per session (1,148 once invoked), scanned A, original, Apache-2.0.

A local command that repeats the project's pull-request CI checks. CI, or continuous integration, automatically checks code changes on a shared service before they are merged.

In plain words
What is it for?
Use it to validate a pull request, run optional end-to-end checks, or post the combined local results as a pull-request comment.
Why use it?
It lets developers check Go, frontend, API, and browser-test results locally without using the project's limited GitHub Actions minutes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is theimaginaryfoundation/what-iff's own configuration. It tells Claude Code how to work on what-iff itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything what-iff configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/ci-local.sh --post --dry-run.

Reuse

Borrowing it

Nothing to install: this file belongs to theimaginaryfoundation/what-iff. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/theimaginaryfoundation/what-iff/main/.claude/skills/ci-local/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/theimaginaryfoundation/what-iff

Made for: Claude Code.

Wrote 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.

agentmods badge for ci-local

README.md
[![agentmods](https://agentmods.dev/badge/skills/theimaginaryfoundation/what-iff/ci-local/github.svg)](https://agentmods.dev/skills/theimaginaryfoundation/what-iff/ci-local)
Your own site
<a href="https://agentmods.dev/skills/theimaginaryfoundation/what-iff/ci-local"><img src="https://agentmods.dev/badge/skills/theimaginaryfoundation/what-iff/ci-local/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.

agentmods 80×15 button for ci-local

Your own site · 80×15
<a href="https://agentmods.dev/skills/theimaginaryfoundation/what-iff/ci-local"><img src="https://agentmods.dev/badge/skills/theimaginaryfoundation/what-iff/ci-local.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,148 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00074 $0.01148
Opus 5 $0.00037 $0.00574
Sonnet 5 $0.00015 $0.00230
Haiku 4.5 $0.00007 $0.00115

Measured yesterday against content hash f19c22c0a75a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ci-local 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.

.claude/skills/ci-local/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ci-local: run the PR CI checks locally, post the results to the PR

Temporary. This skill, scripts/ci-local.sh, and the ci-local / ci-local-post Makefile targets exist only because GitHub Actions minutes are a constraint. Remove all three together once that stops being true. The workflows in .github/workflows/ remain the source of truth for what CI checks; this script just calls the same make targets and npm scripts on the developer machine.

What it replays

Stage CI job Opt-in?
go pr-validation.yml → Validate Go Code (generate, fmt, vet, tidy, check-no-local-models, test-ci + coverage total, build); also skills-check.yml's check-skill-symlinks default
mock-e2e pr-validation.yml → Mock E2E (hermetic, coverage) via scripts/mock-e2e.sh default
frontend frontend-pr-validation.yml (npm ci, SDK schema drift, lint:e2e, e2e:check-configs, tsc, web-unit-coverage + lcov total, build:prod) default
e2e e2e-mock.yml browser (chromium-desktop only) + API Playwright suites against a real API on :8080 with an isolated Postgres --e2e

Not replayed: Codecov upload/validation, the visual-regression project (baselines only match the CI container renderer), other browser shards, and the label-gated real-provider jobs (run-integration, run-local-model). The report footer says so.

Commands

Run the default stages:

make ci-local

Pass flags through ARGS:

make ci-local ARGS="--only go"
make ci-local ARGS="--skip frontend"
make ci-local ARGS="--e2e"            # adds the Playwright stage (needs docker, port 8080 free)
make ci-local ARGS="--verbose"        # stream step output instead of just logging it

Run and post (or update) the sticky PR comment for the current branch's PR:

make ci-local-post
make ci-local-post ARGS="--pr 123"    # explicit PR number

Preview the comment without posting, or re-post the last report without re-running anything:

./scripts/ci-local.sh --post --dry-run
./scripts/ci-local.sh --post-only --pr 123

Read the full file on GitHub · 97 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. yesterday First seen · 97 lines · 74 tokens per session scan A f19c22c0a75a

Subscribe to this mod's changes

ci-local is a skill published in the GitHub repository theimaginaryfoundation/what-iff (15 stars, last pushed yesterday), licensed Apache-2.0. It adds 74 tokens to every session and 1,148 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 2026-09-09.

Related

Other skills, from other repositories

import-prom-rule

Bulk import of a Prometheus alert rule YAML file (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats groups / a plain rules array / a single rule. ⚠️ Do not use this skill for single-rule creation — when the user describes a single alert…

ccfos/nightingale · 125 tokens

chinese-git-workflow

A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.

jnMetaCode/superpowers-zh · 69 tokens

configure-env-variables

Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…

microsoft/power-platform-skills · 119 tokens

atmos-profiles

Atmos profiles: profile directories, --profile and ATMOSPROFILE activation, profile merge behavior, environment switching, and routing profile-specific auth/toolchain/config overrides.

cloudposse/atmos · 35 tokens

webhook-management

Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.

hoangsonww/Claude-Code-Agent-Monitor · 56 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens