protect-ci-workflows

v0.1.0

Guard against an agent weakening the automated checks that review its own work. CI/CD workflow files (.github/workflows/), the composite actions they call (.github/actions/) and the dependency-update automation (.github/dependabot.yml) define what must pass before a change lands -- so rewriting or deleting them is the agent removing the gate that would catch it. The guard refuses shell write-commands targeting those paths; reads pass, and tool-driven regeneration (chock sync) passes. Best-effort and deliberately coarse: the command line is parsed, and a write (a `>`/`>>` redirect, a writer verb like rm/mv/tee/sed -i, cp into the path, git checkout/restore, a PowerShell Set-Content/Add-Content/Out-File) must actually target the protected path; reading it passes. The 'chock: approved-config-change' marker is friction plus an audit trail, not authentication; the check an agent cannot self-approve is server-side branch protection. [Session-enforced via a PreToolUse hook; needs git, a usable bash and a Python 3.11+ (python3, python or py, whichever actually runs; the Windows Store stub is skipped). With no working Python the hook refuses (exit 2); without git or bash, fail-open clients allow silently and fail-closed clients refuse matched commands. If the guard itself crashes or times out, the hook asks for confirmation rather than allowing silently.]

Claude Code1 Skill

By chock-coreLicense: Apache-2.02 GitHub starsUpdated 6 days ago

Directory evidence

Runtimes: Claude Code
Parsed components: 1 skill or MCP entry
Source updated: Sep 30, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install protect-ci-workflows for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install protect-ci-workflows-5@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/open-coder-ai/chock-copilot-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is claude/protect-ci-workflows/.

Plugin files

claude/protect-ci-workflows/

├── .claude-plugin/plugin.json
└── skills/protect-ci-workflows/SKILL.md

Included Skills1

protect-ci-workflowsskills/protect-ci-workflows/SKILL.md

Plugin manifests1

claude/protect-ci-workflows/.claude-plugin/plugin.json

{
  "name": "protect-ci-workflows",
  "description": "Guard against an agent weakening the automated checks that review its own work. CI/CD workflow files (.github/workflows/), the composite actions they call (.github/actions/) and the dependency-update automation (.github/dependabot.yml) define what must pass before a change lands -- so rewriting or deleting them is the agent removing the gate that would catch it. The guard refuses shell write-commands targeting those paths; reads pass, and tool-driven regeneration (chock sync) passes. Best-effort and deliberately coarse: the command line is parsed, and a write (a `>`/`>>` redirect, a writer verb like rm/mv/tee/sed -i, cp into the path, git checkout/restore, a PowerShell Set-Content/Add-Content/Out-File) must actually target the protected path; reading it passes. The 'chock: approved-config-change' marker is friction plus an audit trail, not authentication; the check an agent cannot self-approve is server-side branch protection. [Session-enforced via a PreToolUse hook; needs git, a usable bash and a Python 3.11+ (python3, python or py, whichever actually runs; the Windows Store stub is skipped). With no working Python the hook refuses (exit 2); without git or bash, fail-open clients allow silently and fail-closed clients refuse matched commands. If the guard itself crashes or times out, the hook asks for confirmation rather than allowing silently.]",
  "keywords": [
    "chock",
    "policy-as-code",
    "rule",
    "advise",
    "{'control': 'asi02', 'coverage': 'partial', 'note': 'blocks shell self-modification of ci workflow, action and dependency-automation files; server-side branch protection and required-status-checks remain the backstop an agent cannot self-approve'}"
  ],
  "version": "0.1.0",
  "author": {
    "name": "chock-core"
  },
  "license": "Apache-2.0",
  "repository": "https://github.com/open-coder-ai/chock"
}

Browse the “chock” tag →

agent-discipline

by chock-core

trigger: edits without reading, unverified completion claims, weakened tests, dead code. avoid: skipping verification, deleting assertions, leaving unused code.

Agent Plugins1 Skill

8Updated 3 days ago

block-destructive-commands

by chock-core

Best-effort guard against destructive commands, read as parsed commands (bash -c and cd chains included, echo excluded): rm -rf on absolute, home ($HOME/~) or root-adjacent paths (and PowerShell Remove-Item -Recurse); git push --force (not --force-with-lease), reset --hard, clean -f; kubectl delete; terraform destroy; aws s3 rm --recursive / rb --force; dropdb; helm uninstall/delete; docker volume rm/prune and system prune; gcloud ... delete; find -delete / -exec rm; shred; truncate; wipefs -a. git branch -D asks first. Verbs are matched position-aware, so a bucket or object NAMED like a verb is allowed, and a relative path in the working tree stays allowed. sudo, doas and pkexec are transparent. A pre-push hook refuses any non-fast-forward push -- force, +refspec or lease alike; a human escapes with git push --no-verify. Known bypasses: aliases, an unusual value-flag, interpreters and scripts. Friction, not a security boundary.

Agent Plugins1 Skill

8Updated 3 days ago

block-invisible-unicode

by chock-core

The mechanizable slice of prompt-injection defense, enforced at two points: at commit (the git hook, over staged changes) and at agent tool-use (over a tool call's arguments, as the agent writes) -- invisible and direction-override Unicode. Bidi controls make code read differently than it parses (Trojan Source, CVE-2021-42574); Unicode tag-block characters smuggle instructions that are invisible to a human reviewer but fully legible to the agent reading the file. Zero-width joiners and bidi marks (ZWJ/ZWNJ/LRM/RLM) are deliberately NOT matched -- they are legitimate in emoji sequences and in Persian, Arabic and Indic text -- so ordinary internationalised content passes; only the override/embed/isolate controls and the tag block, which have no honest use in a source tree, are blocked. Escape: 'pragma: allowlist invisible-unicode' on the same line.

Agent Plugins1 Skill

8Updated 3 days ago

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[protect-ci-workflows on Agent Plugins Marketplace](https://pluginsmp.com/plugins/protect-ci-workflows-5)

Directory evidence

Install protect-ci-workflows for Claude Code

Plugin files

Included Skills1

Plugin manifests1

Related plugins

For maintainers

Related plugins