Borrowing it
Nothing to install: this file belongs to dedsecorg/agentic-dns. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dedsecorg/agentic-dns/main/.agents/skills/chunk-sidecar-setup/SKILL.mdgit clone --depth 1 https://github.com/dedsecorg/agentic-dnsWrote 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/dedsecorg/agentic-dns/chunk-sidecar-setup)<a href="https://agentmods.dev/skills/dedsecorg/agentic-dns/chunk-sidecar-setup"><img src="https://agentmods.dev/badge/skills/dedsecorg/agentic-dns/chunk-sidecar-setup/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/dedsecorg/agentic-dns/chunk-sidecar-setup"><img src="https://agentmods.dev/badge/skills/dedsecorg/agentic-dns/chunk-sidecar-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00122 | $0.03449 |
| Opus 5.5 | $0.00049 | $0.01380 |
| Sonnet 5.5 | $0.00024 | $0.00690 |
| Haiku 4.5 | $0.00012 | $0.00345 |
Grade F, and why
chunk-sidecar-setup scanned grade F with 4 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.
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")** -- run `chunk auth status`. If the CircleCI source is `Environment`, update or unset `CIRCLE_TOKEN`, then re-run the status check; do not log in or store another keychain toke Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chunk validate --remote --cmd "curl -fLSs https://raw.githubusercontent.com/CircleCI-Public/circleci-cli/main/install.sh | sudo bash" Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
chunk validate --remote --cmd "curl -fLSs https://raw.githubusercontent.com/CircleCI-Public/circleci-cli/main/install.sh | sudo bash" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
chunk validate --remote --cmd "curl -fLSs https://raw.githubusercontent.com/CircleCI-Public/circleci-cli/main/install.sh | sudo bash" How it starts
The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chunk Sidecar Setup (Onboarding Wizard)
This skill walks you through setting up a chunk sidecar from scratch. A sidecar is a remote Linux container provisioned on CircleCI. It mirrors your local working tree and runs your build, test, and validate commands in a clean, isolated environment -- no local port conflicts, no dependency drift, no "works on my machine."
What you'll have by the end:
- Auth and credentials verified
- A running sidecar with your project's dependencies installed
- A reusable snapshot so future sessions start in seconds
chunk validateconfirmed passing on the sidecar
Work through the stages in order. At each decision point, call AskUserQuestion as specified. Do not skip ahead.
Stage 1 -- Check Prerequisites
Run these three probes and evaluate the results:
chunk --version 2>&1 || echo "CHUNK_NOT_INSTALLED"
chunk auth status 2>&1
cat .chunk/config.json 2>&1 || echo "{}"
chunk --version
If the command is not found, stop and explain: "chunk is not installed or not on your PATH. Install it first (e.g. brew install circleci/tools/chunk on macOS), then re-run this skill."
chunk auth status
Read the output carefully -- it prints the status of each credential:
| Credential | Required for |
|---|---|
| CircleCI | All sidecar commands (required) |
| GitHub | Validate commands that fetch PRs/issues |
| Anthropic | Validate commands that invoke Claude |
If CircleCI shows "Not set", run the OAuth login yourself -- see Logging in below -- then re-run chunk auth status and confirm it shows "Configured" before continuing. For GitHub and Anthropic, surface that they're missing but do not block if the user's validate commands don't need them.
Logging in
OAuth is the default. The user opens a URL, the code comes back over PKCE, and the token lands in the system keychain -- no token pasting.
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 Changed f5c0073851b2
- 1mo ago First seen · 351 lines · 122 tokens per session scan F 608ed15a5911
chunk-sidecar-setup is a skill published in the GitHub repository dedsecorg/agentic-dns (8 stars, last pushed yesterday), licensed MIT. It adds 122 tokens to every session and 3,449 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it F with 4 findings (harvests environment variables, asks for root, downloads and executes remote code). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other skills, from other repositories
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
agent-sandbox
Agent skill for sandbox - invoke with $agent-sandbox.
github-actions-templates
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
moai-ref-secops
DevSecOps, container, and API operational defensive security reference: CI/CD pipeline hardening, secret scanning, IaC misconfiguration detection, SAST/DAST integration, container image scanning, Kubernetes RBAC hardening, container-escape defense, runtime threat detection, OWASP API Top 10 operational defense, WAF…
github-actions
Use when authoring or fixing GitHub Actions CI/CD — workflows under .github/workflows, triggers, job matrix, caching, token permissions, OIDC cloud deploys, environment gates, reusable workflows. NOT the Dockerfile or image build strategy (that is docker), NOT the branching model (that is git-workflow), NOT release…
CI/CD Pipeline Advanced
Expert-level CI/CD pipeline skill for test automation. Covers GitHub Actions, Jenkins, GitLab CI, Azure DevOps, parallel execution, matrix strategies, caching, artifact management, and deployment gates.