AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

New Patch

skill-camjac251-cc-enhanced-new-patch · by camjac251

>-

↗ Repository
— No reviews yet
0 installs
0 views
— view→install

Install

$ agentstack add skill-camjac251-cc-enhanced-new-patch

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README — it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-camjac251-cc-enhanced-new-patch)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● today

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of New Patch? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

/new-patch

Create the four files needed for a new patch, then hand off to the user. $ARGUMENTS is the patch tag.

If the tag is missing, ask the user for tag, one-line purpose, and group.

Files to create

  1. src/patches/.ts: copy the structure from a similar existing patch in src/patches/. Import traverse, @babel/types, and helpers from ./ast-helpers.js. Export a Patch with tag, astPasses, and verify; see src/types.ts for the interface.
  2. src/patches/.test.ts: use node:test plus node:assert/strict. At minimum, assert the exported tag matches and add a placeholder for verify behavior. Mirror the shape of a sibling *.test.ts.
  3. src/patches/index.ts: add the named export ... from "./.js", add the import for the array, and append the patch to allPatches.
  4. src/patch-metadata.ts: add a BY_TAG[""] record with tag, label, and group.

After scaffolding

Tell the user the four files are created. Do not implement the visitor or verifier; that is the user's design step.

Remind them to follow CLAUDE.md > Adding Patches:

  • Step 5: if the patch changes exported live prompt guidance, update src/verification/prompt-surface-rules.ts and update src/verification/prompt-policy-contract.ts for shared policy.
  • Step 6: when the total patch count changes, keep the patch count in sync across the README.md intro and patch-count badge. Confirm the new total against bun run cli --list before pushing.
  • Prompt guidance changes need a patched export, mise run verify:prompt-surfaces -- , human review through prompts:compare, and verify:prompt-drift against a reviewed baseline before drift is called corrected.

Implementation handoff

The implementation phase starts from the current clean upstream bundle, not an older cached snapshot:

mise run native:pull -- latest

Use bun run inspect search versions_clean//cli.js for cli.js anchor discovery, then prove the patch with a focused test, the target matrix (SELECTED_VERSION= mise run verify:patches:matrix), and the native verifier (mise run verify:patches) before calling it complete.

Gotchas

  • This command is slash-only and scaffold-only; do not implement the visitor or verifier inside this workflow.
  • Do not hide this skill behind paths:. The user invokes it by command name before any scaffold files exist.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in AI & ML