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 skills add huybuidac/claude-code-patchkit --skill claude-patchgit clone --depth 1 https://github.com/huybuidac/claude-code-patchkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/huybuidac/claude-code-patchkit/claude-patch)<a href="https://agentmods.dev/skills/huybuidac/claude-code-patchkit/claude-patch"><img src="https://agentmods.dev/badge/skills/huybuidac/claude-code-patchkit/claude-patch/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huybuidac/claude-code-patchkit/claude-patch"><img src="https://agentmods.dev/badge/skills/huybuidac/claude-code-patchkit/claude-patch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00053 | $0.02195 |
| Opus 5.5 | $0.00021 | $0.00878 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 1mo ago), licensed MIT. It adds 53 tokens to every session and 2,195 once invoked, about $0.0002 per session on Opus 5.5. 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
aio-review-deep
Deep multi-agent code review — dispatch a fleet of parallel specialized agents (security, architecture, quality, performance) with GitNexus domain analysis. Use before merging a PR or after a major feature lands when a single-pass review is too shallow. For a quick pre-commit sanity check use aio-review-quick.
aio-starrocks-query-tuning
StarRocks query performance tuning — EXPLAIN plans, Query Profile analysis, operator metrics, tuning recipes, schema optimization, query hints, and text-based profile analysis. Use when diagnosing slow queries, reading EXPLAIN or ANALYZE PROFILE output, finding operator bottlenecks via pipeline metrics, enabling…
aio-golang-mastery
Write, review, and lint Go code. Lint mode runs go build, go vet, golangci-lint, govulncheck, nilaway, deadcode, and race detection (race detector), then applies idiomatic fixes. Reference mode covers concurrency, error handling, generics, testing, gRPC, and production hardening. Use when asked to lint golang, run a…
aio-starrocks-best-practices
StarRocks table design best practices — partitioning strategy, sort key selection, bucketing decisions, Primary Key table tuning, authentication/authorization, and resource group configuration. Use when designing a StarRocks table, reviewing DDL, choosing partition granularity, sizing tablets (tablet sizing), setting…
aio-catch-me-up
Turn Claude into a wise, effective teacher whose only goal is to make sure YOU deeply understand the work an AI agent just did — the problem it solved, why that problem existed, the solution and its design decisions, the edge cases it handled, and the broader impact. Incremental and mastery-gated: it has you restate…
aio-grafana-diagram
Create Grafana diagrams for live system visualization — analyzes codebase to auto-generate Mermaid diagrams with Prometheus metric binding. Each node is colored by health thresholds, turning a static architecture diagram into a live system diagram or service health monitor. Use when you need a dynamic Grafana…