advanced-circleci-mcp-server: Skill for Claude Code

.claude/skills/chunk-sidecar/SKILL.md

chunk-sidecar is a skill for Claude Code from hidetaka-cci/advanced-circleci-mcp-server. It costs 150 tokens per session (3,962 once invoked), scanned C, original, MIT.

A workflow for running build, test, and validation commands in temporary remote Linux environments called CircleCI sidecars.

In plain words
What is it for?
Syncing a project to a sidecar, running tests or validation there, creating sidecars, customizing their environment, and setting up CircleCI Smarter Testing.
Why use it?
It keeps checks away from your computer, avoiding local port conflicts and allowing workspaces to be reset to a known snapshot.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is hidetaka-cci/advanced-circleci-mcp-server's own configuration. It tells Claude Code how to work on advanced-circleci-mcp-server 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 advanced-circleci-mcp-server configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/circleci/workspace/<repo>.

Reuse

Borrowing it

Nothing to install: this file belongs to hidetaka-cci/advanced-circleci-mcp-server. 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/hidetaka-cci/advanced-circleci-mcp-server/main/.claude/skills/chunk-sidecar/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hidetaka-cci/advanced-circleci-mcp-server

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 chunk-sidecar

README.md
[![agentmods](https://agentmods.dev/badge/skills/hidetaka-cci/advanced-circleci-mcp-server/chunk-sidecar/github.svg)](https://agentmods.dev/skills/hidetaka-cci/advanced-circleci-mcp-server/chunk-sidecar)
Your own site
<a href="https://agentmods.dev/skills/hidetaka-cci/advanced-circleci-mcp-server/chunk-sidecar"><img src="https://agentmods.dev/badge/skills/hidetaka-cci/advanced-circleci-mcp-server/chunk-sidecar/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 chunk-sidecar

Your own site · 80×15
<a href="https://agentmods.dev/skills/hidetaka-cci/advanced-circleci-mcp-server/chunk-sidecar"><img src="https://agentmods.dev/badge/skills/hidetaka-cci/advanced-circleci-mcp-server/chunk-sidecar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,962 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00150 $0.03962
Opus 5 $0.00075 $0.01981
Sonnet 5 $0.00030 $0.00792
Haiku 4.5 $0.00015 $0.00396

Measured 10d ago against content hash 84d5e7c89789, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

chunk-sidecar scanned grade C with 1 finding 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 10d 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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

- **Auth errors (401/403, "token invalid", "unauthorized")** — run `chunk auth status` and follow its printed remediation (`chunk auth set circleci` / `github` / `anthropic`). Never dump env vars.
.claude/skills/chunk-sidecar/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chunk Sidecar Skill

Run the user's build, test, and validate commands on a remote chunk sidecar instead of locally. The 90% job is the sync → validate loop. This skill also covers one-time setup (create, snapshot, environment customization).

Sidecars are ephemeral Linux environments provisioned via CircleCI. They isolate work, avoid local port conflicts, and can be reset to known-good snapshots. Your local tree is mirrored to ~/workspace/<repo> on the sidecar each time you sync — the absolute path depends on the SSH user's home (e.g. /home/circleci/workspace/<repo> on cimg/* images, /home/user/workspace/<repo> on the default Ubuntu template). To see the resolved workspace, run chunk sidecar current --json and read the workspace field.

CIRCLE_TOKEN is forwarded over SSH automatically, so authenticated CircleCI API calls work out of the box once a token is configured locally.

The bare default sidecar image does not include the circleci CLI or the circleci-testsuite Smarter Testing plugin. If your validate commands need either, install them during one-time setup (Step 3) and snapshot the result so future sidecars boot with them ready. A snapshot built from a cimg/* base does not include circleci-testsuite either.

Step 1: Prerequisites

Run these checks in order. Stop and report to the user if anything fails.

  1. chunk --version — confirms the CLI is installed and on PATH.
  2. chunk auth status — validates the configured credentials. Rely on the exit code: non-zero means a configured credential failed validation. Zero does not mean every credential is set — a missing CircleCI or GitHub token prints "Not set" and still exits zero. Read the output: if CircleCI shows "Not set", stop and ask the user to run chunk auth set circleci before proceeding (the sidecar commands in Step 2 will otherwise fail with an auth error). The command's output masks tokens; do not dig into env vars yourself.

Do not run echo $CIRCLE_TOKEN, env, printenv, or any other command that reads credential environment variables. That leaks secrets into conversation context. If chunk auth status reports a failure or shows a required credential as "Not set", surface its printed remediation (e.g. "Run chunk auth set circleci") and stop.

Read the full file on GitHub · 200 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. 10d ago First seen · 200 lines · 150 tokens per session scan C 84d5e7c89789

Subscribe to this mod's changes

chunk-sidecar is a skill published in the GitHub repository hidetaka-cci/advanced-circleci-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 150 tokens to every session and 3,962 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). 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

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens