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/konveyor/agentic-controller/verifynpx skills add konveyor/agentic-controller --skill verifygit clone --depth 1 https://github.com/konveyor/agentic-controllerWhat 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 | $0.00058 | $0.01169 |
| Opus 5 | $0.00029 | $0.00584 |
| Sonnet 5 | $0.00012 | $0.00234 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
verify 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Stage
Builds the migrated project, fixes build errors until it compiles, then runs runtime verification to confirm the application actually starts and responds correctly. Grounds its work in the analysis results and the decisions the execute stage recorded. Does NOT re-execute migration steps.
Startup
- Read
docs/plan.md— find the Verification section for build, test, and blackbox commands - Read the
## Executesection of.konveyor/handoff.md— see which steps were applied or failed, and whether execution completed or was aborted - Read
.konveyor/analysis.json— the original violations, so you can confirm the migration addressed them - If execution was aborted or steps failed, log a warning but still attempt verification
Step 1 — Build Verification
Run the build command from docs/plan.md's Verification section.
- Build succeeds: record
build: "passed", proceed to Step 2 - Build fails: enter fix loop
Fix loop
For each build error:
- Read the error message to identify the file and issue
- Read the source file
- Apply a fix
- Never change business logic — if a fix would alter what the code does, record it and stop
- Never remove or stub out methods to make the build pass
Re-run the build after each round of fixes and keep going until it compiles — there is no limit on the number of rounds. Only stop early if an error genuinely cannot be fixed without changing business logic, and record it.
Step 2 — Tests
If a test command exists in the docs/plan.md's Verification section:
- Run the test command
- Record: passed count, failed count, total count
- Do NOT fix failing tests — document them
If no test command exists, record tests: "skipped".
Step 3 — Runtime Verification
If the build passed, run runtime checks. If the build failed, skip this step
and record runtime: "skipped".
3a. Start the application
Use the run command from the docs/plan.md's Verification section, or
detect it from the framework.
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 · 147 lines · 58 tokens per session scan A bb0bb324adc2
verify is a skill published in the GitHub repository konveyor/agentic-controller (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,169 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…