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/huybuidac/claude-code-patchkit/claude-patchnpx skills add huybuidac/claude-code-patchkit --skill claude-patchgit clone --depth 1 https://github.com/huybuidac/claude-code-patchkitWhat 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 | $0.00053 | $0.02195 |
| Opus 5 | $0.00026 | $0.01097 |
| Sonnet 5 | $0.00011 | $0.00439 |
| Haiku 4.5 | $0.00005 | $0.00219 |
Grade A, and why
claude-patch 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 2d 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.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-patch
Binary patches for Claude Code CLI — unlock hard-coded limitations without waiting for upstream changes.
All scanning and patching runs through one cross-platform tool, patches/patch-bin.js. It handles ad-hoc re-signing on macOS and the rename-swap a locked claude.exe needs on Windows, so there are no per-platform scripts to choose between.
node patches/patch-bin.js scan --patch <name> [--bin <path>] # state + derived anchor + guards
node patches/patch-bin.js apply --patch <name> [--bin <path>]
node patches/patch-bin.js revert --patch <name> [--bin <path>]
node patches/patch-bin.js status [--bin <path>] # scan every patch
node patches/patch-bin.js list # registered patch ids
--bin defaults to the resolved claude on PATH. scan exits 1 when the state is abnormal or patched-inert, status when any patch is.
Workflow
- Identify the binary — run
scan; it prints the resolved path, size, and state. Show the user the path andclaude --versionbefore proposing any write. - Select the patch — from the user's argument, or ask. Read
patches/<name>.mdfor what it does and what it is tested on. - Confirm — never write without explicit user confirmation for this specific binary.
- Apply or revert —
applyhandles guard checks, backup, the write, the sidecar, re-signing, and self-verification in one step, and refuses rather than guessing if anything is off. - Report — state the resulting marker count, and that a restart is needed. (Earlier docs claimed
subagent-modeltook effect without one; that was never demonstrated and the one time it was checked, the session had been restarted.)
Never report a patch as working from a marker count alone. Since 2.1.250 a marker can sit in a binary that ignores it — see Bytecode shadowing. scan now catches this, but the durable check is behavioural: claude mcp serve speaks JSON-RPC on stdio, so an initialize + tools/list round-trip prints the live tool schemas without spending a token.
What ships with it
6 files 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.
- 2d ago First seen · 114 lines · 53 tokens per session scan A 1fe96681f0ab
claude-patch is a skill published in the GitHub repository huybuidac/claude-code-patchkit (4 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 2,195 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
token-saver-config
Configure and diagnose token-saver compression settings. Use when the user asks about adjusting compression levels, checking processor status, debugging hook issues, or reviewing savings statistics.
database-migrations
Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Django, TypeORM, golang-migrate). Use when planning or implementing database schema changes.
python-testing
Python testing best practices using pytest including fixtures, parametrization, mocking, coverage analysis, async testing, and test organization. Use when writing or improving Python tests.
docker-patterns
Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration. Use when setting up containerized development environments or reviewing Docker configurations.
python-patterns
Python-specific design patterns and best practices including protocols, dataclasses, context managers, decorators, async/await, type hints, and package organization. Use when working with Python code to apply Pythonic patterns.
search-first
Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Systematizes the "search for existing solutions before implementing" approach. Use when starting new features or adding functionality.