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 LeiGuo622/RetroPatch --skill retropatch-engineeringgit clone --depth 1 https://github.com/LeiGuo622/RetroPatchWrote 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/leiguo622/retropatch/retropatch-engineering)<a href="https://agentmods.dev/skills/leiguo622/retropatch/retropatch-engineering"><img src="https://agentmods.dev/badge/skills/leiguo622/retropatch/retropatch-engineering/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/leiguo622/retropatch/retropatch-engineering"><img src="https://agentmods.dev/badge/skills/leiguo622/retropatch/retropatch-engineering.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 | $0.00117 | $0.00871 |
| Opus 5.5 | $0.00047 | $0.00348 |
| Sonnet 5.5 | $0.00023 | $0.00174 |
| Haiku 4.5 | $0.00012 | $0.00087 |
Grade A, and why
retropatch-engineering 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 2mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retropatch Engineering
Overview
Treat this repository as two linked but separate systems:
- backporting pipeline:
src/backporting.py+src/agent/+src/tools/ - prejudge pipeline:
src/prejudge/
Prefer current code over README text. Some docs and helper scripts are stale.
Route The Task
- Classify the request before editing.
- Change hunk application, patch validation, prompts, or
Projectbehavior: readreferences/repo-map.mdandreferences/runtime-and-validation.md. - Change kernel prejudge logic, CONFIG/arch/fix-commit checks, or LLM necessity judgment: read
references/prejudge-pipeline.md. - Change docs or tests: read
references/known-quirks.mdfirst so you do not preserve existing drift.
- Change hunk application, patch validation, prompts, or
- Run
python3 skills/retropatch-engineering/scripts/check_setup.pybefore claiming the repo is runnable.- Add
--config path/to/config.ymlwhen the task uses a real backport config.
- Add
- Validate narrowly first.
- Start with import or syntax checks.
- Run end-to-end flows only when required and only after reviewing mutation risks.
Follow Working Rules
- Preserve the repo's non-packaged import style unless the task explicitly asks for packaging changes.
- Keep backporting and prejudge edits isolated unless the task clearly spans both.
- Assume end-to-end backporting mutates and cleans the external target repo pointed to by
project_dir; inspectProject._checkout(),Project._apply_hunk(), andmain()before running it. - Fix documentation drift against current code instead of copying existing README commands.
- Update prompt files and the code that binds them together in the same change when tool semantics or model behavior changes.
Use Change Playbooks
Backporting Flow
- Start from
src/backporting.py, thensrc/agent/invoke_llm.py, thensrc/tools/project.py. - Inspect
src/tools/utils.pywhen behavior depends on patch splitting, line matching, or context repair. - Treat
load_yml()as the config contract for required fields and path normalization.
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.
- 2mo ago First seen · 69 lines · 117 tokens per session scan A a214f33b2889
retropatch-engineering is a skill published in the GitHub repository LeiGuo622/RetroPatch (18 stars, last pushed 5mo ago), licensed MIT. It adds 117 tokens to every session and 871 once invoked, about $0.0005 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 2026-08-30.
retropatch-engineering compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| retropatch-engineeringLeiGuo622/RetroPatch | Skill | 18 | 5mo ago | MIT | A | 117 | Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 6d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |