ai-collab-open-system 0.1.0

package/.aict/examples/personal-judgment-growth-assistant/artifacts/execution-prompt.md

@@ -0,0 +1,30 @@
+# Execution prompt - Personal judgment / growth assistant
+
+## Source case
+
+- Case id: `personal-judgment-growth-assistant`
+- Case title: Personal judgment / growth assistant
+- Privacy status: fully synthetic
+- Private material: none
+
+## How to use
+
+Paste this into the selected AI tool after the context package and acceptance card.
+
+## Synthetic content
+
+```text
+Help structure the decision. Do not decide for the user. Separate values, constraints, fears, evidence, and next reversible step.
+```
+
+## Review note
+
+Confirm the prompt does not expand scope beyond acceptance.
+
+## Next step
+
+Run guard review on the first artifact produced from this prompt.
+
+## Why this exists
+
+This artifact makes the case runnable and reviewable. A raw chat can produce a smooth answer, but this file preserves the specific state needed for profile, context, acceptance, guard, handoff, and harvest work.

package/.aict/examples/personal-judgment-growth-assistant/artifacts/guard-review.md

@@ -0,0 +1,28 @@
+# Guard review - Personal judgment / growth assistant
+
+## Source case
+
+- Case id: `personal-judgment-growth-assistant`
+- Case title: Personal judgment / growth assistant
+- Privacy status: fully synthetic
+- Private material: none
+
+## How to use
+
+Use this as the review stance after the first artifact exists. It challenges evidence, privacy, scope, and acceptance alignment.
+
+## Synthetic content
+
+Guard rejects one sentence that says the user should choose the risky project and replaces it with a decision question.
+
+## Review note
+
+A review is not a pass unless it names evidence and residual risk.
+
+## Next step
+
+Fix any blocking finding, then write a handoff note.
+
+## Why this exists
+
+This artifact makes the case runnable and reviewable. A raw chat can produce a smooth answer, but this file preserves the specific state needed for profile, context, acceptance, guard, handoff, and harvest work.

package/.aict/examples/personal-judgment-growth-assistant/artifacts/handoff-note.md

@@ -0,0 +1,28 @@
+# Handoff note - Personal judgment / growth assistant
+
+## Source case
+
+- Case id: `personal-judgment-growth-assistant`
+- Case title: Personal judgment / growth assistant
+- Privacy status: fully synthetic
+- Private material: none
+
+## How to use
+
+Paste this into the next session or tool so work resumes from current state instead of restarting.
+
+## Synthetic content
+
+Current state: decision map complete. Pending: user answers three value questions offline.
+
+## Review note
+
+Check that completed, pending, blocked, and next action are distinguishable.
+
+## Next step
+
+Use the handoff note as input to harvest.
+
+## Why this exists
+
+This artifact makes the case runnable and reviewable. A raw chat can produce a smooth answer, but this file preserves the specific state needed for profile, context, acceptance, guard, handoff, and harvest work.

package/.aict/examples/personal-judgment-growth-assistant/artifacts/harvest-seed.md

@@ -0,0 +1,28 @@
+# Harvest seed - Personal judgment / growth assistant
+
+## Source case
+
+- Case id: `personal-judgment-growth-assistant`
+- Case title: Personal judgment / growth assistant
+- Privacy status: fully synthetic
+- Private material: none
+
+## How to use
+
+Save this after the loop to preserve reusable knowledge without copying private raw material.
+
+## Synthetic content
+
+Reusable pattern: judgment assistance must preserve human agency and make uncertainty explicit.
+
+## Review note
+
+Do not generalize from the synthetic case unless the pattern appears in future work.
+
+## Next step
+
+Move reusable prompts or rules into the appropriate workspace file.
+
+## Why this exists
+
+This artifact makes the case runnable and reviewable. A raw chat can produce a smooth answer, but this file preserves the specific state needed for profile, context, acceptance, guard, handoff, and harvest work.

package/.aict/examples/research-knowledge-synthesis/CASE.md

@@ -0,0 +1,87 @@
+# Research / knowledge synthesis
+
+This is a fully synthetic case. It does not contain private customer material, real raw conversations, local paths, or private operational routes.
+
+## Confusing raw input
+
+A researcher asks several assistants to summarize a market, but sources, assumptions, and unanswered questions blur together.
+
+## Likely single-agent failure
+
+A likely single-agent answer would produce a fluent artifact from the messy request, but it would not preserve explicit context, acceptance, guard review, handoff state, and harvest learning.
+
+## AI Collaboration OS process
+
+1. Context package: Profile: values source-grounded answers and explicit uncertainty. Context: synthetic research on adoption barriers for shared family budgeting tools.
+2. Acceptance card: Done means a three-section synthesis with sourced facts, inferences labeled, unknowns listed, and no claim based on a single weak source.
+3. Execution prompt: Synthesize only from the supplied notes. Mark facts, inferences, and unknowns. Do not fill gaps with market cliches.
+4. Guard review: Guard flags one unsupported segment about willingness to pay and asks to downgrade it to inference.
+5. Handoff note: Synthesis is usable after downgrading willingness-to-pay claim. Next action: gather direct user quotes before treating monetization as proven.
+6. Harvest seed: Reusable pattern: research loops need an evidence table before narrative synthesis.
+
+## Context package
+
+Profile: values source-grounded answers and explicit uncertainty. Context: synthetic research on adoption barriers for shared family budgeting tools.
+
+## Acceptance card
+
+Done means a three-section synthesis with sourced facts, inferences labeled, unknowns listed, and no claim based on a single weak source.
+
+## Guard review
+
+Guard flags one unsupported segment about willingness to pay and asks to downgrade it to inference.
+
+## Handoff note
+
+Synthesis is usable after downgrading willingness-to-pay claim. Next action: gather direct user quotes before treating monetization as proven.
+
+## Harvest seed
+
+Reusable pattern: research loops need an evidence table before narrative synthesis.
+
+## Before/after comparison
+
+A raw chat would hide uncertainty in smooth prose. The workspace preserves source quality and next research gaps.
+
+## Messy starting point
+
+A researcher asks several assistants to summarize a market, but sources, assumptions, and unanswered questions blur together.
+
+## Workspace setup
+
+Use context to separate facts from assumptions, acceptance to require source labels, guard to challenge unsupported claims, and harvest to save reusable search patterns.
+
+## Profile/context
+
+Profile: values source-grounded answers and explicit uncertainty. Context: synthetic research on adoption barriers for shared family budgeting tools.
+
+## Acceptance
+
+Done means a three-section synthesis with sourced facts, inferences labeled, unknowns listed, and no claim based on a single weak source.
+
+## Execution prompt
+
+```text
+Synthesize only from the supplied notes. Mark facts, inferences, and unknowns. Do not fill gaps with market cliches.
+```
+
+## Handoff
+
+Synthesis is usable after downgrading willingness-to-pay claim. Next action: gather direct user quotes before treating monetization as proven.
+
+## Harvest
+
+Reusable pattern: research loops need an evidence table before narrative synthesis.
+
+## What changes compared with a single raw AI chat
+
+A raw chat would hide uncertainty in smooth prose. The workspace preserves source quality and next research gaps.
+
+## Artifacts
+
+- `artifacts/context-package.md`
+- `artifacts/acceptance-card.md`
+- `artifacts/execution-prompt.md`
+- `artifacts/guard-review.md`
+- `artifacts/handoff-note.md`
+- `artifacts/harvest-seed.md`

package/.aict/examples/research-knowledge-synthesis/artifacts/acceptance-card.md

@@ -0,0 +1,28 @@
+# Acceptance card - Research / knowledge synthesis
+
+## Source case
+
+- Case id: `research-knowledge-synthesis`
+- Case title: Research / knowledge synthesis
+- Privacy status: fully synthetic
+- Private material: none
+
+## How to use
+
+Paste this before implementation, drafting, research, or judgment work. Ask the assistant to treat these criteria as the pass/fail surface.
+
+## Synthetic content
+
+Done means a three-section synthesis with sourced facts, inferences labeled, unknowns listed, and no claim based on a single weak source.
+
+## Review note
+
+Reject work that claims completion without evidence tied to this card.
+
+## Next step
+
+Use this card with the execution prompt and later guard review.
+
+## Why this exists
+
+This artifact makes the case runnable and reviewable. A raw chat can produce a smooth answer, but this file preserves the specific state needed for profile, context, acceptance, guard, handoff, and harvest work.

package/.aict/examples/research-knowledge-synthesis/artifacts/context-package.md

@@ -0,0 +1,28 @@
+# Context package - Research / knowledge synthesis
+
+## Source case
+
+- Case id: `research-knowledge-synthesis`
+- Case title: Research / knowledge synthesis
+- Privacy status: fully synthetic
+- Private material: none
+
+## How to use
+
+Paste this before asking an AI tool to continue the task. It gives the assistant the working style, scope, constraints, and known evidence.
+
+## Synthetic content
+
+Profile: values source-grounded answers and explicit uncertainty. Context: synthetic research on adoption barriers for shared family budgeting tools.
+
+## Review note
+
+Check that facts and assumptions are separated before execution starts.
+
+## Next step
+
+Use this context to write or verify the acceptance card.
+
+## Why this exists
+
+This artifact makes the case runnable and reviewable. A raw chat can produce a smooth answer, but this file preserves the specific state needed for profile, context, acceptance, guard, handoff, and harvest work.

package/.aict/examples/research-knowledge-synthesis/artifacts/execution-prompt.md

@@ -0,0 +1,30 @@
+# Execution prompt - Research / knowledge synthesis
+
+## Source case
+
+- Case id: `research-knowledge-synthesis`
+- Case title: Research / knowledge synthesis
+- Privacy status: fully synthetic
+- Private material: none
+
+## How to use
+
+Paste this into the selected AI tool after the context package and acceptance card.
+
+## Synthetic content
+
+```text
+Synthesize only from the supplied notes. Mark facts, inferences, and unknowns. Do not fill gaps with market cliches.
+```
+
+## Review note
+
+Confirm the prompt does not expand scope beyond acceptance.
+
+## Next step
+
+Run guard review on the first artifact produced from this prompt.
+
+## Why this exists
+
+This artifact makes the case runnable and reviewable. A raw chat can produce a smooth answer, but this file preserves the specific state needed for profile, context, acceptance, guard, handoff, and harvest work.

package/.aict/examples/research-knowledge-synthesis/artifacts/guard-review.md

@@ -0,0 +1,28 @@
+# Guard review - Research / knowledge synthesis
+
+## Source case
+
+- Case id: `research-knowledge-synthesis`
+- Case title: Research / knowledge synthesis
+- Privacy status: fully synthetic
+- Private material: none
+
+## How to use
+
+Use this as the review stance after the first artifact exists. It challenges evidence, privacy, scope, and acceptance alignment.
+
+## Synthetic content
+
+Guard flags one unsupported segment about willingness to pay and asks to downgrade it to inference.
+
+## Review note
+
+A review is not a pass unless it names evidence and residual risk.
+
+## Next step
+
+Fix any blocking finding, then write a handoff note.
+
+## Why this exists
+
+This artifact makes the case runnable and reviewable. A raw chat can produce a smooth answer, but this file preserves the specific state needed for profile, context, acceptance, guard, handoff, and harvest work.

package/.aict/examples/research-knowledge-synthesis/artifacts/handoff-note.md

@@ -0,0 +1,28 @@
+# Handoff note - Research / knowledge synthesis
+
+## Source case
+
+- Case id: `research-knowledge-synthesis`
+- Case title: Research / knowledge synthesis
+- Privacy status: fully synthetic
+- Private material: none
+
+## How to use
+
+Paste this into the next session or tool so work resumes from current state instead of restarting.
+
+## Synthetic content
+
+Synthesis is usable after downgrading willingness-to-pay claim. Next action: gather direct user quotes before treating monetization as proven.
+
+## Review note
+
+Check that completed, pending, blocked, and next action are distinguishable.
+
+## Next step
+
+Use the handoff note as input to harvest.
+
+## Why this exists
+
+This artifact makes the case runnable and reviewable. A raw chat can produce a smooth answer, but this file preserves the specific state needed for profile, context, acceptance, guard, handoff, and harvest work.

package/.aict/examples/research-knowledge-synthesis/artifacts/harvest-seed.md

@@ -0,0 +1,28 @@
+# Harvest seed - Research / knowledge synthesis
+
+## Source case
+
+- Case id: `research-knowledge-synthesis`
+- Case title: Research / knowledge synthesis
+- Privacy status: fully synthetic
+- Private material: none
+
+## How to use
+
+Save this after the loop to preserve reusable knowledge without copying private raw material.
+
+## Synthetic content
+
+Reusable pattern: research loops need an evidence table before narrative synthesis.
+
+## Review note
+
+Do not generalize from the synthetic case unless the pattern appears in future work.
+
+## Next step
+
+Move reusable prompts or rules into the appropriate workspace file.
+
+## Why this exists
+
+This artifact makes the case runnable and reviewable. A raw chat can produce a smooth answer, but this file preserves the specific state needed for profile, context, acceptance, guard, handoff, and harvest work.

package/.aict/guard/EXAMPLE.synthetic.md

@@ -0,0 +1,51 @@
+# Guard / Review Filled Synthetic Example
+
+## Purpose
+
+Challenge work against requirements, risks, privacy boundaries, evidence quality, and user intent before it becomes trusted output.
+
+## When to use
+
+Use after a draft, implementation, research answer, plan, or handoff that could mislead future work if wrong.
+
+## Input shape
+
+The artifact under review, acceptance card, context package, known constraints, and the specific review stance.
+
+## Output shape
+
+A review result with findings, severity, evidence, required fixes, and a pass or reject recommendation.
+
+## Copy-paste prompt
+
+Use `PROMPT.md` with the synthetic input below.
+
+## Blank template
+
+Use `TEMPLATE.md` for your own task.
+
+## Filled synthetic example
+
+Artifact reviewed: Onboarding checklist draft.
+
+Review stance: First-user path and privacy review.
+
+Acceptance source: Acceptance card dated synthetic-case-01.
+
+Findings: P1 checklist says 'review analytics' but privacy constraint forbids adding analytics now.
+
+Evidence: Context states no analytics SDK until privacy language is reviewed.
+
+Required fixes: Replace analytics step with manual tester observation.
+
+Residual risk: Still untested with a real user.
+
+Recommendation: Reject until the flow uses privacy-safe evidence.
+
+## Common failure modes
+
+See `FAILURE_MODES.md`.
+
+## How to hand it to Claude Code / Codex / Cursor / Windsurf / Copilot / Cline
+
+Paste this example into any tool with `../adapters/SHARED_CORE_CONTRACT.md` to see the expected shape.

package/.aict/guard/FAILURE_MODES.md

@@ -0,0 +1,40 @@
+# Guard / Review Common Failure Modes
+
+## Purpose
+
+Challenge work against requirements, risks, privacy boundaries, evidence quality, and user intent before it becomes trusted output.
+
+## When to use
+
+Read this before trusting a guard / review artifact.
+
+## Input shape
+
+The artifact plus the original context and acceptance card.
+
+## Output shape
+
+A short list of risks to fix before reuse.
+
+## Copy-paste prompt
+
+Ask your AI tool: "Check this guard / review artifact against the failure modes below and name the first concrete fix."
+
+## Blank template
+
+Use `TEMPLATE.md` to rewrite the artifact.
+
+## Filled synthetic example
+
+Use `EXAMPLE.synthetic.md` to compare a safe example.
+
+## Common failure modes
+
+- Reviewing style instead of requirements.
+- Letting the same assistant rubber-stamp its own work.
+- Listing vague concerns without actionable fixes.
+- Calling something passed without checking the acceptance card.
+
+## How to hand it to Claude Code / Codex / Cursor / Windsurf / Copilot / Cline
+
+Paste this file after the artifact and ask for findings ordered by risk.

package/.aict/guard/PROMPT.md

@@ -0,0 +1,47 @@
+# Guard / Review Prompt
+
+## Purpose
+
+Challenge work against requirements, risks, privacy boundaries, evidence quality, and user intent before it becomes trusted output.
+
+## When to use
+
+Use after a draft, implementation, research answer, plan, or handoff that could mislead future work if wrong.
+
+## Input shape
+
+The artifact under review, acceptance card, context package, known constraints, and the specific review stance.
+
+## Output shape
+
+A review result with findings, severity, evidence, required fixes, and a pass or reject recommendation.
+
+## Copy-paste prompt
+
+```text
+Review this artifact against the context and acceptance card. Prioritize concrete defects, missing evidence, privacy risk, unsupported claims, and scope drift. Return findings ordered by severity with file or section references when possible.
+
+Input:
+[paste your redacted task material here]
+
+Output shape:
+A review result with findings, severity, evidence, required fixes, and a pass or reject recommendation.
+
+Rules:
+- Keep private material local and redacted.
+- Label facts and assumptions.
+- If information is missing, ask at most three concrete questions.
+- Make the result usable in Claude Code / Codex / Cursor / Windsurf / Copilot / Cline.
+```
+
+## Blank template
+
+Use `TEMPLATE.md`.
+
+## Filled synthetic example
+
+Use `EXAMPLE.synthetic.md`.
+
+## Common failure modes
+
+Use `FAILURE_MODES.md`.

package/.aict/guard/README.md

@@ -0,0 +1,44 @@
+# Guard / Review
+
+How output is challenged before trust.
+
+中文：让另一个视角先挑错，再决定是否相信产物。
+
+## Purpose
+
+Challenge work against requirements, risks, privacy boundaries, evidence quality, and user intent before it becomes trusted output.
+
+## When to use
+
+Use after a draft, implementation, research answer, plan, or handoff that could mislead future work if wrong.
+
+## Input shape
+
+The artifact under review, acceptance card, context package, known constraints, and the specific review stance.
+
+## Output shape
+
+A review result with findings, severity, evidence, required fixes, and a pass or reject recommendation.
+
+## Copy-paste prompt
+
+See `PROMPT.md`. The prompt is designed to work in Claude Code / Codex / Cursor / Windsurf / Copilot / Cline.
+
+## Blank template
+
+See `TEMPLATE.md`.
+
+## Filled synthetic example
+
+See `EXAMPLE.synthetic.md`.
+
+## Common failure modes
+
+See `FAILURE_MODES.md`.
+
+## How to hand it to Claude Code / Codex / Cursor / Windsurf / Copilot / Cline
+
+1. Open the adapter for your tool in `../adapters/`.
+2. Include `../adapters/SHARED_CORE_CONTRACT.md`.
+3. Paste this layer's `PROMPT.md` plus either `TEMPLATE.md` or `EXAMPLE.synthetic.md`.
+4. Ask the tool to return the layer's output shape exactly.

package/.aict/guard/TEMPLATE.md

@@ -0,0 +1,60 @@
+# Guard / Review Template
+
+## Purpose
+
+Challenge work against requirements, risks, privacy boundaries, evidence quality, and user intent before it becomes trusted output.
+
+## When to use
+
+Use after a draft, implementation, research answer, plan, or handoff that could mislead future work if wrong.
+
+## Input shape
+
+The artifact under review, acceptance card, context package, known constraints, and the specific review stance.
+
+## Output shape
+
+A review result with findings, severity, evidence, required fixes, and a pass or reject recommendation.
+
+## Copy-paste prompt
+
+Open `PROMPT.md` and paste this completed template below it.
+
+## Blank template
+
+### Artifact reviewed:
+
+
+### Review stance:
+
+
+### Acceptance source:
+
+
+### Findings:
+
+
+### Evidence:
+
+
+### Required fixes:
+
+
+### Residual risk:
+
+
+### Recommendation:
+
+
+
+## Filled synthetic example
+
+See `EXAMPLE.synthetic.md`.
+
+## Common failure modes
+
+See `FAILURE_MODES.md`.
+
+## How to hand it to Claude Code / Codex / Cursor / Windsurf / Copilot / Cline
+
+Use the adapter in `../adapters/` and include the shared core contract.

package/.aict/handoff/EXAMPLE.synthetic.md

@@ -0,0 +1,51 @@
+# Handoff Filled Synthetic Example
+
+## Purpose
+
+Transfer current state, decisions, evidence, blockers, and next actions to another session or tool without replaying the whole conversation.
+
+## When to use
+
+Use before stopping, switching tools, delegating to another assistant, or after any work that may need continuation.
+
+## Input shape
+
+Goal, current status, completed work, changed files or artifacts, decisions, verification evidence, blockers, and next action.
+
+## Output shape
+
+A short handoff note that separates done, pending, blocked, and unverified work.
+
+## Copy-paste prompt
+
+Use `PROMPT.md` with the synthetic input below.
+
+## Blank template
+
+Use `TEMPLATE.md` for your own task.
+
+## Filled synthetic example
+
+Goal: Finish synthetic onboarding checklist.
+
+Current status: Draft exists and failed guard review on privacy-safe evidence.
+
+Completed: Context package and acceptance card are ready.
+
+Pending: Replace analytics step with manual tester observation.
+
+Blocked: Need owner choice on whether account creation belongs in scope.
+
+Decisions: First loop focuses on first note creation only.
+
+Verification evidence: Guard review found one P1 issue.
+
+Next action: Edit checklist step 4 and rerun guard review.
+
+## Common failure modes
+
+See `FAILURE_MODES.md`.
+
+## How to hand it to Claude Code / Codex / Cursor / Windsurf / Copilot / Cline
+
+Paste this example into any tool with `../adapters/SHARED_CORE_CONTRACT.md` to see the expected shape.