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/openshift/lightspeed-agentic-operator/rebase-cleannpx skills add openshift/lightspeed-agentic-operator --skill rebase-cleangit clone --depth 1 https://github.com/openshift/lightspeed-agentic-operatorWhat 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 | $0.01156 |
| Opus 5 | $0.00026 | $0.00578 |
| Sonnet 5 | $0.00011 | $0.00231 |
| Haiku 4.5 | $0.00005 | $0.00116 |
Grade A, and why
rebase-clean 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Rebase Workflow
Use this workflow exactly for rebases in this repository.
Rules
- Do not create extra temporary branches unless the user explicitly asks.
- Do not make unrelated edits.
- Do not stop after analysis; finish rebase and validation.
- Keep output brief and operational.
- Never assume target branch names; detect current branch first.
- Use
go test ./... -count=1from the repo root (this repo has nomake testwrapper).
Step 0: Detect Branch Context
- Run
git branch --show-current. - Treat detected current branch as the candidate target branch.
- Ask user to confirm explicitly before proceeding:
I detected '<current-branch>' as the current branch. Should I rebase this branch?
- If user specified a target branch, verify it matches current branch; if not, stop and ask.
- Do not run reset/rebase commands until this confirmation is received.
- Before any reset/rebase command, restate:
- current branch
- target branch
- approved baseline ref and confirm when there is any mismatch or ambiguity.
Step 1: Restore Branch Baseline (Rerun Only)
Use this step only when a prior rebase attempt failed or introduced unwanted edits. For a first rebase attempt, skip this step and go directly to Step 2.
- Checkout target branch.
- Hard reset to the known backup/base commit the user approved.
- Fetch
upstream.
Command pattern:
git checkout <branch>
git reset --hard <backup-or-approved-base>
git fetch upstream
Step 2: Rebase Onto Main
Run:
git rebase upstream/main
If conflicts occur, resolve only the conflicted files. Do not add extra refactors.
Step 3: Conflict Resolution Policy
For each conflicted file:
- Start from one side (
oursortheirs) as a temporary base. - Apply only minimal compatibility changes required to compile and run tests on the new base branch.
- Keep behavior from the feature commit unless it is incompatible with upstream removals/renames.
- Resolve matching tests together with production code changes.
- Avoid opportunistic refactors during conflict resolution.
- Go module conflicts: If
go.modorgo.sumconflict, prefertheirs(upstream) and rungo mod tidyafter.
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 · 149 lines · 53 tokens per session scan A 4d13f9d47861
rebase-clean is a skill published in the GitHub repository openshift/lightspeed-agentic-operator (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,156 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…