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/safe-code-changenpx skills add openshift/lightspeed-agentic-operator --skill safe-code-changegit 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 | $0.00049 | $0.00809 |
| Opus 5 | $0.00024 | $0.00404 |
| Sonnet 5 | $0.00010 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
safe-code-change 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safe Code Change
After a code change is made, find and fix affected tests before running validation.
Rules
- The code change is already done. Do not modify production code.
- Only update tests to match the new behavior, not the other way around.
- Do not reformat or lint-fix during test updates. Save that for validation.
- If a test change is ambiguous (unclear what the new expected behavior is), ask the user.
Step 1: Identify What Changed
git diff --name-only
git diff --stat
List the modified production files (ignore test files, configs, docs).
Step 2: Find Affected Tests
Search for imports and uses of changed functions/types across all test files:
# Find test files that import the changed package
rg "github.com/openshift/lightspeed-agentic-operator/<changed_package>" --type go -g '*_test.go'
# Find direct function/type references
rg "<ChangedFunctionOrType>" --type go -g '*_test.go'
For controller or CLI changes, also check:
- Shared test helpers or fixtures under the same package
examples/YAMLs only if behavior affects documented shapes (usually not test code)
Step 3: Analyze Impact on Tests
For each affected test file, check whether the change breaks existing tests:
- Signature changes — function renamed, parameters added/removed/reordered.
- Behavior changes — return value, error messages, side effects differ.
- Removed code — tests for deleted functions/types need removal.
- New code — consider whether new tests are needed (ask user if unclear).
- Interface changes — mock implementations need updating.
Step 4: Update Tests
Apply minimal fixes to each affected test:
For Ginkgo Tests (if present):
- Update
Expect()assertions to match new return values - Update mock return values in test fixtures
- Add/remove parameters in function calls
- Update error message checks
- Adjust
Eventually()timeouts if reconciliation logic changed
For Standard Go Tests (typical in this repo):
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 · 109 lines · 49 tokens per session scan A 11daf7061d0f
safe-code-change is a skill published in the GitHub repository openshift/lightspeed-agentic-operator (10 stars, last pushed 2d ago), licensed Apache-2.0. It adds 49 tokens to every session and 809 once invoked, about $0.0002 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…