Add experimental ExecFence skill#385
Open
chrystyan96 wants to merge 5 commits into
Open
Conversation
ExecFence gives Codex a repeatable workflow for adding local execution guardrails before dev, build, test, CI, package, and agent tool execution in persistent projects. Tested: python skills/.system/skill-creator/scripts/quick_validate.py skills/.experimental/execfence
The ExecFence CLI is now published on npm and has a GitHub Pages documentation site, so the experimental skill should point agents at those canonical entry points. The OpenAI interface metadata also now follows the default-prompt convention by explicitly mentioning $execfence. Tested: python skills/.system/skill-creator/scripts/quick_validate.py skills/.experimental/execfence
ExecFence 3.1 adds automatic project guard mode, so the experimental OpenAI skill should prefer guard enable for broad project setup while keeping direct init/run commands available for narrower adoption. Tested: python skills/.system/skill-creator/scripts/quick_validate.py skills/.experimental/execfence
The OpenAI skill should state the new recommended adoption path directly so agents prefer guard mode instead of only individual commands. Scope-risk: narrow Tested: git diff --check
The skill should not assume guard mode exists in every published ExecFence CLI version, so it now treats guard as the preferred path for v3.1.0+ and keeps the existing init/scan/run fallback. Constraint: npm latest may lag the project PR that introduces guard mode Scope-risk: narrow Tested: git diff --check Tested: frontmatter and required skill files parsed with a local format check
Author
|
@codex review |
|
Codex Review: Didn't find any major issues. Bravo. ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
execfence scan,execfence ci, andexecfence run -- <command>npx --yes execfence guard enableand project-local rules for automatic build/dev/test protection when the installed CLI supports itExecFence Automatic Guard Mode Summary
The related ExecFence project PR introduces a dry-run-first automatic guard mode for persistent projects. The skill now treats this as the preferred path for ExecFence v3.1.0+ and keeps
init/scan/run/coverage/wireas the fallback whenguardis unavailable.npx --yes execfence guard enableshows a project-local protection plan without writing filesnpx --yes execfence guard enable --applyapplies reversible wrappers, CI wiring, and project-local agent rulesnpx --yes execfence guard statusreports protected and unprotected entrypointsnpx --yes execfence guard disableremoves only changes ExecFence can identify as generated by ExecFencenpx --yes execfence guard global-enableinstalls global skill/defaults and agent rules only; it does not alter PATH, aliases, shims, shell profiles, or globally intercept package managers/shell commandsThis means the skill should guide agents toward guard mode for broad adoption, while the npm CLI remains the component that actually scans, blocks, writes reports, and returns exit codes.
Review / Validation
git diff --checkSKILL.mdfrontmatter exists,name: "execfence"matches folder,LICENSE.txtexists, andagents/openai.yamlexistsupstream/mainis limited toskills/.experimental/execfence/{SKILL.md,LICENSE.txt,agents/openai.yaml}execfencenpm package