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 OpenLAIR/OpenSkill --skill evo-patch-generate-applygit clone --depth 1 https://github.com/OpenLAIR/OpenSkillWrote 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/openlair/openskill/evo-patch-generate-apply)<a href="https://agentmods.dev/skills/openlair/openskill/evo-patch-generate-apply"><img src="https://agentmods.dev/badge/skills/openlair/openskill/evo-patch-generate-apply/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/openlair/openskill/evo-patch-generate-apply"><img src="https://agentmods.dev/badge/skills/openlair/openskill/evo-patch-generate-apply.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 | $0.00068 | $0.00467 |
| Opus 5 | $0.00034 | $0.00234 |
| Sonnet 5 | $0.00014 | $0.00093 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
evo-patch-generate-apply 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.
What it actually says
Patch Generate & Apply Skill
Generates and applies unified diff patches for code fixes.
When to Use
- You need to generate a patch file from code changes
- You need to apply a .diff/.patch file to a repository
- Automating code fixes via the diff/patch workflow
Workflow
- Generate diff using
generate_unified_diff()with a/b prefixes - Handle EOF using
handle_no_newline_at_eof()for POSIX compliance - Write patch using
write_patch_file()to create patch_N.diff - Apply patch using
apply_patch()with git apply and fallbacks - Validate using
validate_patch_applied()to confirm changes - Batch apply using
apply_all_patches()for multiple patches
Key Functions
All functions are in scripts/patch.py:
generate_unified_diff(original, modified, file_path)- Creates git-compatible unified diffhandle_no_newline_at_eof(diff_lines)- Adds missing EOF newline markerswrite_patch_file(diff_content, output_dir, index)- Writes patch_N.diffapply_patch(patch_path, target_dir)- Applies via git apply with fallbacksvalidate_patch_applied(file_path, expected_content)- Confirms patch workedapply_all_patches(patch_dir, target_dir)- Applies all patches in order
Important Notes
- Use splitlines(keepends=True) to preserve trailing newlines
- Always add a/ and b/ prefixes for git apply compatibility
- Handle "No newline at end of file" marker manually
- git apply uses -p1 by default to strip a/ b/ prefixes
- Use --3way flag as fallback for context mismatches
Reference
See references/domain_reference.md for detailed domain knowledge.
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 · 47 lines · 68 tokens per session scan A 63a3b833c948
evo-patch-generate-apply is a skill published in the GitHub repository OpenLAIR/OpenSkill (90 stars, last pushed yesterday), licensed Apache-2.0. It adds 68 tokens to every session and 467 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 2026-09-11.
Other skills, from other repositories
resolving-merge-conflicts
Use when a git merge or rebase reports conflicts and the operation is in progress.
yesresearch
Autonomous research loop — read plan, decompose, dispatch research agents, integrate, deliver wiki. For research tasks instead of coding. Runs as visible TUI agents in git worktree. Use when user says "yesresearch", "research ", "recherchiere ". Spawns cluster agents that use opencode built-in subagents (general…
yesloop
Autonomous task loop — analyze, plan, execute, verify, review, finish. Runs as visible TUI agent in git worktree. Use when user says "yesloop", "loop", "run it autonomously".
dos-verify-done-claims
Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.
Workspace Git Hygiene
Inspect branch and status, protect user edits, and avoid destructive git commands.
Using Git Worktrees
Create or use an isolated worktree for feature work so concurrent edits do not collide.