Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/sambhram1/ghostpatch-/ghostpatchnpx skills add Sambhram1/Ghostpatch- --skill ghostpatchgit clone --depth 1 https://github.com/Sambhram1/Ghostpatch-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 | $0.00067 | $0.01278 |
| Opus 5 | $0.00034 | $0.00639 |
| Sonnet 5 | $0.00013 | $0.00256 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
ghostpatch scanned grade A with 0 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
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.
Ghostpatch
Ghostpatch helps an agent do supervised open-source contribution work end to end.
It can:
- find GitHub issues worth solving
- qualify candidates before spending time on them
- solve locally with Codex, Claude, or a local deterministic agent
- run validation commands
- create or reuse your fork for live contribution work
- prepare or publish issues and PRs with safety checks
- remember prior PR context for CI failures and maintainer follow-up
The skill is the main interface. The npm package @sambhram06/ghostpatch is the engine behind it.
Who It Is For
Use Ghostpatch when you want:
- supervised help contributing to open-source repositories
- a repeatable scan -> review -> solve -> publish workflow
- explicit autonomous mode only when you ask for it
Requirements
- Node.js 22 or newer
- Git
- GitHub CLI
GH_TOKENorGITHUB_TOKENfor live GitHub scan and publish- Optional: Codex CLI or Claude CLI
Install
Install the skill from skills.sh:
npx skills add https://github.com/Sambhram1/Ghostpatch- --skill ghostpatch
Optional but faster engine install:
npm install -g @sambhram06/ghostpatch
First Run
The shortest successful path is:
ghostpatch setup
ghostpatch scan --live
ghostpatch review
What happens in setup:
- choose your agent:
local,codex, orclaude - choose languages and repositories
- choose whether to use
GH_TOKENorGITHUB_TOKEN - validate the token if it is already present
- save only the variable name, not the token itself
If the skill runner path is needed directly:
node <skill-folder>/scripts/ghostpatch.mjs setup
node <skill-folder>/scripts/ghostpatch.mjs scan --live
node <skill-folder>/scripts/ghostpatch.mjs review
Normal Workflow
Ghostpatch's default workflow is supervised:
- scan for candidates
- review the ranked opportunities
- ask the configured agent to solve locally
- run validation
- inspect blockers, warnings, and generated drafts
- publish only after explicit confirmation
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 200 lines · 67 tokens per session scan A 134f6cf93039
ghostpatch is a skill published in the GitHub repository Sambhram1/Ghostpatch- (2 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 1,278 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…