tas/Codewalkers
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: Update agent.md to reflect prompt overhaul

Browse Source 
Remove CODEBASE_VERIFICATION references, document new shared constants
(TEST_INTEGRITY, SESSION_STARTUP, PROGRESS_TRACKING), update mode prompt
descriptions with TDD protocol, Definition of Done checklists, and
mandatory test specifications.
This commit is contained in:
Lukas May
2026-02-18 17:21:57 +09:00
parent 9ed7e9ad16
commit 44d2a3ff08
1 changed files with 11 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
docs/agent.md
View File

@@ -24,7 +24,7 @@
| `accounts/` | Account discovery, config dir setup, credential management, usage API |
| `credentials/` | `AccountCredentialManager` — credential injection per account |
| `lifecycle/` | `LifecycleController` — retry policy, signal recovery, missing signal instructions |
| `prompts/` | Mode-specific prompt builders (execute, discuss, plan, detail, refine) + shared blocks (codebase verification, deviation rules, git workflow) + inter-agent communication instructions |
| `prompts/` | Mode-specific prompt builders (execute, discuss, plan, detail, refine) + shared blocks (test integrity, deviation rules, git workflow, session startup, progress tracking) + inter-agent communication instructions |
## Key Flows
@@ -178,21 +178,23 @@ Mode-specific prompts in `prompts/` are composed from shared blocks and mode-spe
| `SIGNAL_FORMAT` | Signal output format (done/questions/error via `.cw/output/signal.json`) |
| `INPUT_FILES` | Input file structure (manifest, assignment files, context files) |
| `ID_GENERATION` | `cw id` usage for generating entity IDs |
| `CODEBASE_VERIFICATION` | "Training as hypothesis" pattern — read before writing, verify imports, follow patterns, check git log |
| `TEST_INTEGRITY` | Non-negotiable test rules — no self-validating tests, no assertion mutation, no skipping, independent tests, full suite runs |
| `SESSION_STARTUP` | Environment verification sequence — confirm working directory, check git state, establish green test baseline, read assignment |
| `PROGRESS_TRACKING` | Maintain `.cw/output/progress.md` after each commit — survives context compaction |
| `DEVIATION_RULES` | Decision tree for handling unexpected situations (typo→fix, bug→fix if small, missing dep→coordinate, architectural mismatch→STOP) |
| `GIT_WORKFLOW` | Worktree-aware git guidance with rationale (frequent commits as recovery checkpoints, descriptive messages, specific staging to avoid cross-agent conflicts, no force-push) |
| `CONTEXT_MANAGEMENT` | Context compaction awareness (don't stop early, commit as checkpoints, parallel file reads) |
| `GIT_WORKFLOW` | Worktree-aware git guidance — specific file staging (no `git add .`), no force-push, check status first |
| `CONTEXT_MANAGEMENT` | Parallel file reads, cross-reference to progress tracking |
| `buildInterAgentCommunication()` | Per-agent CLI instructions for `cw listen`, `cw ask`, `cw answer` (compact format with usage pattern summary) |
### Mode Prompts
| Mode | File | Key Sections |
|------|------|-------------|
| **execute** | `execute.ts` | Execution protocol (read→orient→test first→implement→verify→commit→signal), scope rules with rationale (7+ files = overscoping), codebase verification, deviation rules, git workflow, context management, anti-patterns (including anti-hardcoding) |
| **plan** | `plan.ts` | Dependency graph with wave analysis, file ownership for parallelism, specificity test ("Could a detail agent break this down?") |
| **detail** | `detail.ts` | Specificity test with good/bad examples, file ownership constraints, task sizing (1-5 files good, 7+ split), checkpoint guidance |
| **discuss** | `discuss.ts` | Goal-backward analysis (outcome→artifacts→wiring→failure points), question quality examples, decision quality examples, read-before-asking |
| **refine** | `refine.ts` | Improvement hierarchy (ambiguity > missing details > contradictions > unverifiable > missing edge cases), don't refine style, signal done if nothing to improve |
| **execute** | `execute.ts` | Session startup (baseline verification), execution protocol (RED-GREEN-REFACTOR: write failing tests→implement→verify→commit→iterate), test integrity rules, anti-patterns (self-validating tests, test mutation), scope rules (7+ files = overscoping), deviation rules, git workflow, progress tracking, Definition of Done checklist |
| **plan** | `plan.ts` | Testing strategy (tests per phase, not trailing phase), dependency graph with wave analysis, file ownership for parallelism, specificity test, Definition of Done checklist |
| **detail** | `detail.ts` | Mandatory test specifications (file path, scenarios, run command) for execute tasks, specificity test with good/bad examples, file ownership constraints, task sizing by lines changed, checkpoint guidance, Definition of Done checklist |
| **discuss** | `discuss.ts` | Goal-backward analysis (outcome→artifacts→wiring→failure points), question quality examples, decision quality with verification criteria, testability & verification question category, Definition of Done checklist |
| **refine** | `refine.ts` | Improvement hierarchy (ambiguity > missing details > contradictions > unverifiable requirements with testable acceptance criteria > missing edge cases as testable scenarios), Definition of Done checklist |
### Execute Prompt Dispatch