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/cxcscmu/skilllearnbench/git-patch-workflownpx skills add cxcscmu/SkillLearnBench --skill git-patch-workflowgit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWhat 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 | $0.00022 | $0.00625 |
| Opus 5 | $0.00011 | $0.00313 |
| Sonnet 5 | $0.00004 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
git-patch-workflow 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Patch Workflow
Creating Patch Files
Method 1: From Unstaged Changes
cd /path/to/repo
git diff path/to/file.java > /path/to/patch/fix.patch
Method 2: From Staged Changes
git diff --cached > /path/to/patch/fix.patch
Method 3: From Commits
# Create patch from last N commits
git format-patch -N HEAD
# Create patch from specific commit
git show COMMIT_HASH > /path/to/patch/fix.patch
Patch File Structure
A unified diff patch looks like:
--- a/original/path/file.java
+++ b/modified/path/file.java
@@ -10,5 +10,6 @@ class MyClass {
// context line
- old code here
+ new code here
// context line
Key components:
---prefix: original file+++prefix: modified file@@markers: line numbers and context-prefix: removed lines+prefix: added lines- No prefix: context lines
Applying Patches
Basic Application
cd /path/to/repo
patch -p1 < /path/to/patch/fix.patch
With Error Handling
# Dry-run to test application
patch -p1 --dry-run < /path/to/patch/fix.patch
# Apply with strict checking
patch -p1 < /path/to/patch/fix.patch
# Apply with less strict checking
patch -p0 < /path/to/patch/fix.patch
Best Practices
- Use Git Format: Create patches via
git difforgit format-patchfor consistency - Include Context: Ensure adequate context lines (3+ lines around changes)
- Test Patches: Always dry-run before applying to ensure compatibility
- Modular Patches: Create separate patches for logically independent changes
- Clear Names: Name patches descriptively (e.g.,
fix-javascript-security-bypass.patch) - Document Changes: Include explanation of what the patch fixes
Verifying Application
# Check if patch was applied
git status
git diff HEAD
# Verify specific file was patched
git show HEAD:path/to/file.java | grep "your fix"
Multiple Patches
For multiple related patches:
# Create patches in order
git diff HEAD~2 HEAD~1 > patch1.patch
git diff HEAD~1 HEAD > patch2.patch
# Apply in sequence
patch -p1 < patch1.patch
patch -p1 < patch2.patch
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 · 103 lines · 22 tokens per session scan A 0dcf37567830
git-patch-workflow is a skill published in the GitHub repository cxcscmu/SkillLearnBench (80 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 625 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
creating-skills
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Letta Code's capabilities with specialized knowledge, workflows, or tool integrations.
Context Doctor
Identify and repair degradation in system prompt, external memory, and skills preventing you from following instructions or remembering information as well as you should.
image-generation
Generate images from text prompts (and optionally edit/remix input images). Use when the user asks to create, generate, draw, render, or edit an image, illustration, logo, icon, diagram, or photo.
adding-models
Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update model-specific compatibility behavior. Covers runtime catalog sources, CI test matrices, and handle validation.
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
writing-bench-task-judge
Use when writing or modifying checkgoals() / getanswer() / App check methods in benchenv/task/, or when reviewing a draft task's judge correctness. Triggers include adding a new task, editing a judge method, or diagnosing a judge false-positive/negative.