the workflow library

pr-risk-review

{"t2-invoice-chaser":"nika: v1\nworkflow:\n  id: invoice-chaser\n  description: \"Ledger CSV → overdue filter → drafted reminders → human gate → drafts file\"\n\nmodel: ollama/qwen3.5:4b   # local · zero key · swap for groq/llama-3.3-70b (drafting is a fast-model job)\n\nvars:\n  ledger_csv: \"./finance/invoices.csv\"\n\ntasks:\n  ledger:\n    invoke:\n      tool: \"nika:read\"\n      args: { path: \"${{ vars.ledger_csv }}\" }\n\n  rows:\n    with:\n      csv: ${{ tasks.ledger.output }}\n    invoke:\n      tool: \"nika:convert\"\n      args:\n        input: \"${{ with.csv }}\"\n        from: csv\n        to: json\n        has_header: true\n\n  overdue:\n    with:\n      rows: ${{ tasks.rows.output }}\n    invoke:\n      tool: \"nika:jq\"\n      args:\n        input: \"${{ with.rows }}\"\n        expression: 'map(select(.status == \"overdue\"))'\n\n  drafts:\n    with:\n      overdue: ${{ tasks.overdue.output }}\n    when: ${{ size(with.overdue) > 0 }}\n    infer:\n      prompt: |\n        Draft one short, polite payment reminder per overdue invoice ·\n        ${{ with.overdue }}\n        Markdown · one section per client · firm but warm.\n\n  approve:\n    with:\n      drafts: ${{ tasks.drafts.output }}\n    when: ${{ with.drafts != null }}   # nothing drafted · nothing to approve\n    invoke:\n      tool: \"nika:prompt\"\n      args:\n        message: \"Save the reminder drafts for sending?\"\n        default: false\n\n  save:\n    with:\n      drafts: ${{ tasks.drafts.output }}\n      approved: ${{ tasks.approve.output }}\n    when: ${{ with.drafts != null && with.approved == true }}   # zero overdue → drafts skipped (null) · don't write nothing\n    invoke:\n      tool: \"nika:write\"\n      args:\n        path: \"./finance/reminders-to-send.md\"\n        content: \"${{ with.drafts }}\"\n\noutputs:\n  overdue:\n    value: ${{ tasks.overdue.output }}\n    description: \"The overdue rows the reminders were drafted for\"\n","t4-deep-research-brief":"nika: v1\nworkflow:\n  id: deep-research-brief\n  description: \"plan → budgeted research agent → thinking synthesis → brief on disk\"\n\nmodel: ollama/qwen3.5:4b   # local default · per-task overrides below pick stronger models\n\nvars:\n  topic:\n    type: string\n    required: true\n    description: \"What to research\"\n\ntasks:\n  plan:\n    infer:\n      model: anthropic/claude-haiku-4-5    # planning is a fast-model job\n      prompt: \"Break '${{ vars.topic }}' into 4 sharp research queries · no overlap.\"\n      schema:\n        type: object\n        required: [queries]\n        properties:\n          queries:\n            type: array\n            items: { type: string }\n\n  investigate:\n    with:\n      plan_queries: ${{ tasks.plan.output.queries }}\n    agent:\n      system: |\n        You are a rigorous researcher. Work the queries one by one ·\n        fetch sources · keep verbatim quotes · note what each source\n        actually supports. Call nika:done when the plan is exhausted.\n      prompt: \"Research plan · ${{ with.plan_queries }}\"\n      tools:\n        - \"nika:fetch\"                 # the web\n        - \"nika:write\"                 # scratch notes\n        - \"nika:done\"                  # the loop-completion sentinel\n      max_turns: 25\n      max_tokens_total: 150000\n      schema:\n        type: object\n        required: [findings, sources]\n        properties:\n          findings:\n            type: array\n            items: { type: string }\n          sources:\n            type: array\n            items: { type: string }\n\n  brief:\n    with:\n      investigate_findings: ${{ tasks.investigate.output.findings }}\n      investigate_sources: ${{ tasks.investigate.output.sources }}\n    infer:\n      prompt: |\n        Findings · ${{ with.investigate_findings }}\n        Sources · ${{ with.investigate_sources }}\n        Write the executive brief · what's true · what's contested ·\n        what it means · what to do. Two pages max.\n      thinking:\n        enabled: true\n        budget_tokens: 8000\n\n  save:\n    with:\n      brief: ${{ tasks.brief.output }}\n    invoke:\n      tool: \"nika:write\"\n      args:\n        path: \"./research/${{ vars.topic }}.md\"\n        content: \"${{ with.brief }}\"\n        create_dirs: true\n\noutputs:\n  brief: ${{ tasks.brief.output }}\n  sources:\n    value: ${{ tasks.investigate.output.sources }}\n    description: \"Every source the agent actually used\"\n","t3-localization-factory":"nika: v1\nworkflow:\n  id: localization-factory\n  description: \"glob docs → parallel read → parallel translate → mirror tree\"\n\nmodel: ollama/qwen3.5:4b   # local default · swap for mistral/mistral-large (EU model for EU locales)\n\nvars:\n  lang: \"fr\"\n  source_glob: \"./docs/**/*.md\"\n\ntasks:\n  files:\n    invoke:\n      tool: \"nika:glob\"\n      args:\n        pattern: \"${{ vars.source_glob }}\"\n        exclude: [\"**/node_modules/**\"]\n\n  texts:\n    with:\n      files: ${{ tasks.files.output }}\n    for_each: ${{ with.files }}\n    max_parallel: 8\n    invoke:\n      tool: \"nika:read\"\n      args: { path: \"${{ item }}\" }\n\n  pairs:\n    with:\n      files: ${{ tasks.files.output }}\n      texts: ${{ tasks.texts.output }}\n    invoke:\n      tool: \"nika:jq\"\n      args:\n        input: [\"${{ with.files }}\", \"${{ with.texts }}\"]\n        expression: \"transpose | map({path: .[0], text: .[1]})\"\n\n  translated:\n    with:\n      pairs: ${{ tasks.pairs.output }}\n    for_each: ${{ with.pairs }}\n    max_parallel: 3                    # rate-limit the provider\n    fail_fast: false                   # finish the batch · a failed file yields null at its index\n    on_error:\n      recover: null                    # null keeps the transpose zip aligned (order preserved)\n    infer:\n      prompt: |\n        Translate to ${{ vars.lang }} · keep markdown structure, code blocks\n        untouched, and the original tone ·\n        ${{ item.text }}\n\n  bundle:\n    with:\n      pairs: ${{ tasks.pairs.output }}\n      translated: ${{ tasks.translated.output }}\n    invoke:\n      tool: \"nika:jq\"\n      args:\n        input: [\"${{ with.pairs }}\", \"${{ with.translated }}\"]\n        expression: \"transpose | map(select(.[1] != null)) | map({path: .[0].path, text: .[1]})\"\n\n  mirror:\n    with:\n      bundle: ${{ tasks.bundle.output }}\n    for_each: ${{ with.bundle }}\n    max_parallel: 8\n    invoke:\n      tool: \"nika:write\"\n      args:\n        path: \"./i18n/${{ vars.lang }}/${{ item.path }}\"\n        content: \"${{ item.text }}\"\n        create_dirs: true\n\noutputs:\n  files:\n    value: ${{ tasks.files.output }}\n    description: \"Every source file that was mirrored\"\n"}

scores a diff’s blast radius, probes only when it’s high. This file carries a real recorded trace — the home page replays it, beat for beat, from the run record.

4tasksthe plan below walks them
3wavesrun together when they can
exec · infer · agent · invokeverbsthe whole grammar it speaks
recordeda real runthe trace is the proof

the plan

derived from the file, never drawn by hand

diffexec

riskinfer

probeagentreportinvoke

the file, whole

pr-risk-review.nika.yaml

1nika: v12workflow:3  id: pr-risk-review4# local model · the diff never leaves5model: ollama/llama3.2:3b67# the file IS the blast radius8permits:9  ▷exec: [ git ]10  fs: { write: [ ./review.md ] }11  tools: [ "nika:read", "nika:write" ]1213tasks:14  diff:15    ▷exec: { command: [ git, diff, main ] }1617  risk:18    with:19      diff: ${{ tasks.diff.output }}20    timeout: "120s"21    ◇infer:22      prompt: "Score this diff's blast radius from 0 to 10: ${{ with.diff }}"23      schema:24        type: object25        required: [ score, reasons ]26        properties:27          score: { type: number }28          reasons: { type: array, items: { type: string } }29      max_tokens: 4003031  probe:32    with:33      score: ${{ tasks.risk.output.score }}34      reasons: ${{ tasks.risk.output.reasons }}35    when: ${{ with.score >= 7 }}36    ✦agent:37      prompt: "Trace the risky call paths behind: ${{ with.reasons }}"38      tools: [ "nika:read" ]39      max_turns: 34041  report:42    with:43      review: ${{ tasks.risk.output }}44    ◆invoke:45      tool: "nika:write"46      args: { path: ./review.md, content: "${{ with.review }}" }4748outputs:49  review: "${{ tasks.risk.output }}"50

lines 31–35: when: the probe only fires on real risk. Source: the served copy · byte-pinned to the recorded trace by the honesty suite · open it in the playground →

Watch the recorded one replay on the home page, walk the showcase gallery, or install and run the file yourself.