

Also from Kynth Studios


Also from Kynth Studios


Also from Kynth Studios
1# AI-DLC Adaptive Workflow Rule23> Inspired by the [AI-Driven Development Life Cycle (AI-DLC)](https://github.com/awslabs/aidlc-workflows) methodology. This rule embeds adaptive software development practices into every Cline session.45## Core Philosophy67**The workflow adapts to the work, not the other way around.**89Not every request needs a full development lifecycle. A one-line bug fix shouldn't go through requirements analysis. But a new multi-service application shouldn't start with code either. This rule ensures the right level of rigor is applied automatically.1011---1213## 🚨 Mandatory: Complexity Assessment1415**Before starting ANY software development task**, you MUST perform a silent complexity assessment. This takes seconds and determines how much process to apply.1617### Assessment Criteria1819Evaluate the request against these dimensions:2021| Dimension | Low (1) | Medium (2) | High (3) |22|-----------|---------|------------|----------|23| **Scope** | Single file/function | Multiple files/components | Multiple services/systems |24| **Risk** | No breaking changes | Could break existing features | Affects production data/users |25| **Ambiguity** | Crystal clear intent | Some questions needed | Significant unknowns |26| **Architecture** | Fits existing patterns | Minor new patterns | New architecture needed |27| **User Impact** | Internal/developer only | Indirect user impact | Direct user-facing changes |2829### Complexity Tiers3031**Sum the scores across all 5 dimensions:**3233- **Score 5–7 → FAST TRACK**: Proceed directly to implementation. No ceremony needed.34- **Score 8–11 → STANDARD**: Lightweight planning, then implement with approval gates.35- **Score 12–15 → FULL LIFECYCLE**: Execute the complete Inception → Construction flow.3637---3839## Fast Track (Score 5–7)4041For simple, clear, low-risk requests. Get in, build it, get out.4243**Process:**441. Confirm understanding of the request with a brief summary.452. Implement the change.463. Verify it works (run tests, lint, build).474. Present the result.4849**Examples:** Bug fixes, small features, config changes, dependency updates, documentation updates, refactoring within a single module.5051---5253## Standard Track (Score 8–11)5455For moderate complexity work that benefits from a plan but doesn't need full lifecycle treatment.5657**Process:**5859### 1. Lightweight Planning (2–5 minutes)60- Summarize the requirements in 3–5 bullet points.61- Identify the components/files that will be affected.62- Note any risks or dependencies.63- Present the plan to the user for approval.6465### 2. Implementation with Gates66- Create a code generation plan (checklist of files to create/modify).67- Get user approval on the plan.68- Implement the approved plan.69- Write tests alongside the implementation.7071### 3. Verification72- Run build and tests.73- Present results with a summary of what was done.7475**Examples:** New feature with 2–3 components, API integration, database schema changes, moderate refactoring across multiple files.7677---7879## Full Lifecycle (Score 12–15)8081For complex, high-risk, or ambiguous work that needs the full AI-DLC treatment.8283**Process:**8485### 🔵 Inception Phase86Execute these stages, adapting depth to the specific project:87881. **Workspace Detection** — Scan the codebase, determine greenfield/brownfield, identify tech stack.89902. **Requirements Analysis** — Gather and document requirements:91 - Functional requirements (what should it do?)92 - Non-functional requirements (performance, security, scalability)93 - Constraints and assumptions94 - Write to `aidlc-docs/inception/requirements/requirements.md`95963. **User Stories** (if user-facing) — Generate stories with acceptance criteria:97 - Personas, stories in As-a/I-want/So-that format98 - Acceptance criteria in Given-When-Then format99 - Write to `aidlc-docs/inception/user-stories/user-stories.md`1001014. **Application Design** (if new architecture needed) — Design the system:102 - Component architecture and relationships103 - Data models and API contracts104 - Technology decisions with rationale105 - Write to `aidlc-docs/inception/application-design/`1061075. **Units of Work** (if multi-component) — Break down into buildable units:108 - Define scope, dependencies, and build order for each unit109 - Write to `aidlc-docs/inception/units-of-work.md`110111**Each stage has an approval gate.** Present findings, get user approval, then proceed.112113### 🟢 Construction Phase114For each unit of work:1151161. **Functional Design** (if complex logic) — Design data models, business rules, interfaces before coding.1171182. **NFR Assessment** (if performance/security/scale matters) — Identify requirements and design patterns.1191203. **Code Generation** (always) — Two parts:121 - **Plan**: Checklist of files, functions, dependencies → get approval122 - **Execute**: Build the approved plan, writing tests alongside code1231244. **Build & Test** — After all units: verify build, run tests, report results.125126**Each stage has an approval gate.** Present work, get approval, then proceed.127128---129130## Approval Gates131132At every significant decision point, you MUST pause and get explicit user approval before proceeding. This is non-negotiable at all complexity tiers.133134**Approval gate format:**135136```137[Stage] Complete — [Brief Summary]138139Key outputs: [what was produced]140Key decisions: [what was decided]141142How would you like to proceed?143```144145Present clear options (approve / request changes / discuss further).146147**Rules:**148- NEVER proceed to the next stage without approval.149- NEVER silently skip a stage — always explain why a stage is being skipped and confirm.150- If the user wants to override the recommended tier (e.g., "just build it"), respect their choice but note what's being skipped.151152---153154## Progress Tracking155156For Standard and Full Lifecycle tracks, maintain an `aidlc-docs/aidlc-state.md` file that records:157158```markdown159# AI-DLC State160161## Project Context162- Request: [original user request]163- Complexity: [Fast Track / Standard / Full Lifecycle] (Score: N)164- Workspace: [Greenfield / Brownfield]165- Started: [timestamp]166167## Stage Progress168- [x] Complexity Assessment169- [x/⏭️] Stage Name — [Completed / Skipped: reason]170- [ ] Next Stage171...172```173174Update this file after each stage completion. This enables session continuity — if the conversation resets, read this file to resume where you left off.175176---177178## Audit Trail179180For Full Lifecycle track, maintain an `aidlc-docs/audit.md` that logs every significant interaction:181182```markdown183## [Stage Name]184**Timestamp**: [ISO 8601]185**User Input**: "[exact user input]"186**AI Action**: "[what was done]"187**Decision**: "[what was decided and why]"188---189```190191This creates accountability and traceability for complex projects.192193---194195## Key Principles1961971. **Adapt, don't impose.** Match the process to the work. Never apply heavy process to simple tasks.1982. **Plan before you code** — but only as much as the situation demands.1993. **The human is always in control.** Propose, don't dictate. Every gate needs approval.2004. **Document decisions, not just code.** Future-you (or future-Cline) needs to understand WHY, not just WHAT.2015. **Complete each unit fully** before starting the next. Don't scatter partial implementations across the codebase.2026. **Test alongside code.** Tests are not an afterthought — they're part of code generation.2037. **Fail fast, iterate.** If something isn't working at the design stage, catch it there — not after 500 lines of code.204
One repository carrying more than one format is the comparison this product exists for: does anyone actually write different content in each file, or is one a copy of the other?
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| cline/prompts.clinerules/audio-plugin-developer.md · 1.2k | Cline rules | styleperformancedo-notagent-behaviour | 57/100 | today | |
| cline/prompts.clinerules/ba.md · 1.2k | Cline rules | archgitagent-behaviour | 50/100 | today | |
| cline/prompts.clinerules/baby-steps.md · 1.2k | Cline rules | do-notagent-behaviour | 50/100 | today | |
| cline/prompts.clinerules/c#-guide.md · 1.2k | Cline rules | style | 27/100 | today | |
| cline/prompts.clinerules/claude-code-subagents.md · 1.2k | Cline rules | testarchdo-notagent-behaviour | 77/100 | today | |
| cline/prompts.clinerules/cline-architecture.md · 1.2k | Cline rules | archtypesapi | 54/100 | today | |
| cline/prompts.clinerules/cline-continuous-improvement-protocol.md · 1.2k | Cline rules | testgitperformance | 58/100 | today | |
| cline/prompts.clinerules/cline-for-research.md · 1.2k | Cline rules | agent-behaviour | 34/100 | today | |
| cline/prompts.clinerules/cline-for-slides.md · 1.2k | Cline rules | setupbuildstylearch+1 | 86/100 | today | |
| cline/prompts.clinerules/cline-for-webdev-ui.md · 1.2k | Cline rules | archagent-behaviour | 58/100 | today | |
| cline/prompts.clinerules/code-review.md · 1.2k | Cline rules | lint-formatgitsecurityperformance | 48/100 | today | |
| cline/prompts.clinerules/codebase-onboarding.md · 1.2k | Cline rules | lint-formatstylearchdependencies | 56/100 | today | |
| cline/prompts.clinerules/comprehensive-slide-dev-guide.md · 1.2k | Cline rules | buildarchtypesui | 62/100 | today | |
| cline/prompts.clinerules/create-documentation.md · 1.2k | Cline rules | apidocs | 44/100 | today | |
| cline/prompts.clinerules/gemini-comprehensive-software-engineering-guide.md · 1.2k | Cline rules | buildstyletesting-strategysecurity+4 | 36/100 | today | |
| cline/prompts.clinerules/general-development-rules.md · 1.2k | Cline rules | stylegitdeploymentdo-not | 73/100 | today | |
| cline/prompts.clinerules/google-apps-script-developer.md · 1.2k | Cline rules | setupstylegitsecurity+3 | 66/100 | today | |
| cline/prompts.clinerules/helm-chart-developer.md · 1.2k | Cline rules | setuplint-formatstylearch+6 | 81/100 | today | |
| cline/prompts.clinerules/mcp-development-protocol.md · 1.2k | Cline rules | setupteststyle | 73/100 | today | |
| cline/prompts.clinerules/mcp_env_configuration.md · 1.2k | Cline rules | setupstylearchsecurity+1 | 77/100 | today |
A badge carrying the measured quality of the strongest agent config file in this repository, out of 100. It reads from this index every time somebody loads your page, so it changes when the measurement changes and there is nothing to keep up to date. Free, no account, and the value is not something you or we can set by hand.
[](https://rulestack.kynth.studio/configs/cline-prompts-clinerules-ai-dlc-adaptive-workflow)Would rather not hotlink us? Every badge is also served in shields.io’s endpoint schema, so shields renders the image and your readers never talk to our domain:
Published by Toolproof, the masthead over this index and eight others. The method behind the number is at toolproof.kynth.studio/methodology, and the whole thing is readable as JSON with no key at /api.