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/restarter/lets-workflow/opinion-workflownpx skills add restarter/lets-workflow --skill opinion-workflowgit clone --depth 1 https://github.com/restarter/lets-workflowWhat 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 | $0.00057 | $0.01110 |
| Opus 5 | $0.00028 | $0.00555 |
| Sonnet 5 | $0.00011 | $0.00222 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
opinion-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
opinion-workflow (Dynamic Workflow asset)
A Dynamic Workflow asset (see CLAUDE.md -> "Dynamic Workflow Assets"; review-workflow is the reference example). opinion.workflow.js is executed by the Workflow tool, invoked from /lets:opinion's Workflow Mode via:
Workflow({ scriptPath: "${CLAUDE_PLUGIN_ROOT}/skills/opinion-workflow/opinion.workflow.js", args })
${CLAUDE_PLUGIN_ROOT} is substituted at command-load time, so opinion.md carries the literal absolute path. Treat opinion.workflow.js as a template the command points at, not a script to reproduce inline.
What it does (off-context)
A multi-stage chain so per-agent opinions never enter the conversation - only the final aggregate returns:
- Opine - fan out the selected
lets:<name>experts in parallel (structuredOPINION_SCHEMA: per-option scores 1-5, recommended option, risks, confidence, reasoning). - Tally (pure logic) - aggregate -> options ranked by recommendation plurality (average score is only a tiebreak), so
leading= the most-recommended option (the same axisunanimous/weakConsensususe). Zero opinions -> no leading (recommendationsurfaces as null, never a phantom first option). The option-id allowlist also feedsOPINION_SCHEMA/CHALLENGE_SCHEMAas a runtime enum, so agents can only emit valid ids. - Challenge (CONDITIONAL) - runs ONLY when
weakConsensus(not unanimous, or any low-confidence vote). Re-dispatch the same experts to argue the strongest case AGAINST the leading option (CHALLENGE_SCHEMA). Strong consensus -> skipped. - Synthesize -
decideRecommendationapplies the asymmetric rule: a strong adversarial signal (majoritywould_change_pickathighseverity converging on one better option - convergence judged over the high-severity votes only, against real option ids so a hallucinated id can't win) flips the pick; otherwise the leading option is confirmed with the strongest counter attached as a caveat. If the challenge was dispatched but every critic errored (zero usable votes),outcomeischallenge_failed(the analog of review'sverify_failed) - the leading option is surfaced as NOT stress-tested, never silently confirmed.
What ships with it
1 file 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.
- 3d ago First seen · 47 lines · 57 tokens per session scan A 45d10deb00ed
opinion-workflow is a skill published in the GitHub repository restarter/lets-workflow (17 stars, last pushed 10d ago), licensed MIT. It adds 57 tokens to every session and 1,110 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 2026-08-30.
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…