Consolidate the attention-filters skill (122 lines) into check-phase, reducing check-phase from 234 to 110 lines. Removed verbose bash code blocks, 30-line consolidated output example, re-check protocol (belongs in act-phase), and motivational section. Updated all references in README, plugin.json, using-archeflow, and colette-bridge.
4.8 KiB
name, description
| name | description |
|---|---|
| check-phase | Use when acting as Guardian, Skeptic, Sage, or Trickster in the Check phase. Defines review rules, finding format, attention filters, and spawning protocol. |
Check Phase
Reviewers examine the Maker's implementation. This skill defines shared rules, finding format, and spawning protocol.
Shared Rules
- Review against the proposal's intended design, not invented requirements.
- Read actual code via
git diffon the Maker's branch. - Use the finding format below for every issue.
- Give a clear verdict:
APPROVEDorREJECTEDwith rationale. STATUS: DONEsignals agent completion.APPROVED/REJECTEDis domain output. Both are parsed independently.
Finding Format
| Location | Severity | Category | Description | Fix |
|---|---|---|---|---|
| src/auth/handler.ts:48 | CRITICAL | security | Empty string bypasses validation | Add length check |
Severity: CRITICAL = must fix, blocks approval. WARNING = should fix, doesn't block alone. INFO = nice to have, never blocks.
Categories: security reliability design breaking-change dependency quality testing consistency
Evidence Requirements
Every CRITICAL or WARNING must include concrete evidence. Without evidence, downgrade to INFO.
Valid evidence: command output, exit codes, code citations with line numbers, git diff excerpts, reproduction steps.
Banned in CRITICAL/WARNING: "might be", "could potentially", "appears to", "seems like", "may not". Rewrite with evidence or downgrade.
For each CRITICAL/WARNING, state: (1) what was tested, (2) what was observed, (3) what correct behavior should be.
Attention Filters
Each archetype receives only relevant context. Do not pass everything.
| Archetype | Receives | Excludes |
|---|---|---|
| Guardian | Maker's git diff + proposal risk section + test results | Explorer research, Creator rationale, other reviewers |
| Skeptic | Creator's proposal (assumptions + architecture) + confidence scores | Git diff, Explorer research, other reviewers |
| Sage | Creator's proposal + Maker's diff + implementation summary + test results | Explorer raw research, other reviewer verdicts |
| Trickster | Maker's git diff + attack surface summary (file types + entry points) | Proposal, research, other reviewers |
Token budget targets:
| Archetype | Fast | Standard | Thorough |
|---|---|---|---|
| Guardian | 1500 | 2000 | 2500 |
| Skeptic | skip | 1500 | 2000 |
| Trickster | skip | skip | 1500 |
| Sage | skip | 2500 | 3000 |
Context isolation: Agents receive fresh, controller-constructed context only. No session bleed, no cross-agent contamination, no ambient knowledge. Verify zero references to excluded artifacts before spawning.
Cycle-back filtering (cycle 2+): Pass structured feedback table only (not full reviewer artifacts). Strip resolved items. Cap at 500 tokens — summarize by severity if exceeded.
Reviewer Spawning Protocol
Step 1: Guardian First (mandatory)
Guardian always runs first. It receives the Maker's git diff and the proposal's risk section only.
Save output to .archeflow/artifacts/${RUN_ID}/check-guardian.md.
Step 2: A2 Fast-Path Evaluation
After Guardian completes, count CRITICAL and WARNING findings in its output. If both are zero, and not escalated, and not first cycle of a thorough workflow — skip remaining reviewers and proceed to Act phase.
Step 3: Parallel Remaining Reviewers
If A2 does not trigger, spawn remaining reviewers in parallel:
| Workflow | Reviewers (after Guardian) |
|---|---|
fast |
None (Guardian only) |
fast (escalated) |
Skeptic + Sage |
standard |
Skeptic + Sage |
thorough |
Skeptic + Sage + Trickster |
Each reviewer gets context per the attention filters above.
Step 4: Collect and Consolidate
For each reviewer: save to .archeflow/artifacts/${RUN_ID}/check-<archetype>.md, emit review.verdict event, record sequence number.
Deduplication: If two reviewers raise the same issue (same file + same category), merge into one finding using the higher severity. Don't double-count.
Verdict: Count CRITICAL findings across all reviewers (after dedup). Any CRITICAL = REJECTED. Otherwise APPROVED.
Example consolidated output:
## Check Phase Results — Cycle 1
### Guardian: APPROVED
| Location | Severity | Category | Description | Fix |
|----------|----------|----------|-------------|-----|
| src/auth.ts:52 | WARNING | security | Missing rate limit | Add rate limiter |
### Verdict: APPROVED — 0 critical, 1 warning
Timeout Handling
Each reviewer has a 5-minute timeout. On timeout: emit agent.complete with "error": true, log WARNING, treat as no findings, proceed.
Exception: Guardian timeout is blocking — abort Check phase and report to user.