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/vthinkdeveloper/vthink-agent-toolkit/work-towards-alignment-simplenpx skills add vthinkdeveloper/vthink-agent-toolkit --skill work-towards-alignment-simplegit clone --depth 1 https://github.com/vthinkdeveloper/vthink-agent-toolkitWhat 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 | $0.00060 | $0.01417 |
| Opus 5 | $0.00030 | $0.00709 |
| Sonnet 5 | $0.00012 | $0.00283 |
| Haiku 4.5 | $0.00006 | $0.00142 |
Grade A, and why
work-towards-alignment-simple 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
work-towards-alignment-simple
A two-phase collaborative alignment session. User-paced, never declares alignment unilaterally. All output is plain markdown.
Inputs
- Argument: a path to a plan/design doc, a PR number, or a short topic description.
- If unclear, ask the user to specify before doing anything else.
Workflow
Two phases. Phase A is chat-only — no files written. Phase B writes one markdown file and walks claims.
Phase A — Chat-only knowledge probe
Step 1 — Read and internalize
Read the source artefact. Identify:
- 5–10 load-bearing claims the user must actively agree with (root causes, decisions, trade-offs, scope boundaries, verification steps).
- Per-claim prerequisites — the specific concepts the user must understand to evaluate each claim. Be concrete: name classes, annotations, patterns — not vague terms like "Spring" or "auth".
Do not write any file yet. Hold everything in working memory.
Tell the user in one short paragraph: how many items you found, what their titles are, and that you're about to probe basics before writing anything.
Step 2 — Probe with AskUserQuestion (one prerequisite at a time)
For each prerequisite, issue one AskUserQuestion:
Question: "Point N rests on [PREREQUISITE]. Where are you on this?"
Header: "Prereq N.k"
Options:
- "I know it" → skip teaching, move on
- "Teach me" → 5–15 line explanation with concrete examples
- "Partially" → 2-line refresher, then confirm
Rules:
- One prerequisite per call. Never bundle.
- Finish all of Point N's prerequisites before moving to Point N+1.
- If the user says "skip basics / just write the doc", honor it and jump to Phase B — log which items had basics skipped.
Step 3 — Phase A wrap-up
After all prerequisites are probed, say in chat (one short paragraph):
"Phase A done. [count] prereqs known, [count] taught. Writing the alignment doc now."
Then move to Phase B.
Phase B — Write the markdown doc and walk claims
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 · 171 lines · 60 tokens per session scan A 0ceeb350b93d
work-towards-alignment-simple is a skill published in the GitHub repository vthinkdeveloper/vthink-agent-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,417 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…