Phase Context Loading Protocol
This skill defines skill loading tiers to optimize token consumption while preserving automation capabilities.
[!IMPORTANT]
Single Source of Truth for Skill Loading Strategy.
Reference this skill to understand WHEN to load WHICH skills.
TIER 0: System Foundation — ALWAYS LOADED
[!CAUTION]
NEVER lazy-load TIER 0 skills. They enable core automation.
These skills MUST be available in EVERY session at bootstrap.
| Skill |
Tokens |
Why Always Load |
core-principles |
~519 |
Anti-hallucination rules, Stub-First, Documentation First |
skill-safe-commands |
~927 |
Enables automation — mv, ls, git, tests auto-run |
artifact-management |
~636 |
Archiving protocol, file management, dual state tracking |
| TOTAL |
~2,082 |
Non-negotiable system foundation |
TIER 0 Loading Rule
- Load at session bootstrap (via
GEMINI.md / .cursorrules)
- These skills are loaded BEFORE any phase begins
- Never remove or defer loading of TIER 0 skills
TIER 1: Phase-Triggered — Load on Phase Entry
These skills are phase-specific and loaded when entering the corresponding phase.
| Phase |
Skills to Load |
Approx. Tokens |
| Analysis |
requirements-analysis, skill-task-model, artifact-formalizer (contract only), (skill-archive-task if new task) |
~3,100-4,000 |
| Architecture |
architecture-design, artifact-formalizer (contract only), (architecture-format-core OR -extended) |
~2,850-4,200 |
| Planning |
planning-decision-tree, skill-planning-format, tdd-stub-first, artifact-formalizer (contract only) |
~2,525 |
| Development |
developer-guidelines, documentation-standards |
~1,100 |
| Review |
Phase-specific -review-checklist skill |
~300-400 |
| Security |
security-audit |
~500 |
| VDD |
vdd-adversarial, (adversarial-* per workflow) |
~1,000-2,500 |
TIER 1 Loading Conditions
Analysis Phase:
requirements-analysis — When 02_analyst activatedskill-task-model — When creating/updating TASK.mdskill-archive-task — When existing TASK.md detected AND new (unrelated) task
Architecture Phase:
architecture-design — When 04_architect activatedarchitecture-format-core — Default for most updatesarchitecture-format-extended — Load ONLY for:
- Creating NEW system from scratch
- Major refactor (>3 components affected)
- User explicitly requests "full architecture template"
Planning Phase:
planning-decision-tree — When 06_planner activatedskill-planning-format — When creating PLAN.mdtdd-stub-first — When stub creation starts
Development Phase:
developer-guidelines — When 08_developer activateddocumentation-standards — When updating docs
Review Phase:
- Load the appropriate
*-review-checklist for the current review type
Every authoring phase (Analysis, Architecture, Planning):
artifact-formalizer — load references/authoring-contract.md before the first sentence of
any artifact is written. Load the SKILL.md body and the scanner only when auditing an artifact
that already exists.- Why. The contract is ~1,100 tokens; auditing an artifact afterwards costs a full re-read of
that artifact plus the rewrite. Measured cost of the late order:
artifact-formalizer/references/measurement-baseline.md §5.
TIER 2: Extended — Load Only When Explicitly Requested
These skills are specialized and loaded only when explicitly invoked by user or workflow.
| Skill |
Tokens |
Loading Condition |
architecture-format-extended |
~3,000 |
New system / major refactor / user requests full template |
skill-reverse-engineering |
~1,322 |
User requests "sync docs with code" / docs-code mismatch |
skill-update-memory |
~1,101 |
Post-development phase, .AGENTS.md updates needed |
skill-adversarial-security |
~838 |
VDD workflow with security focus |
skill-adversarial-performance |
~946 |
VDD workflow with performance focus |
vdd-sarcastic |
~145 |
VDD workflow with sarcastic mode |
Integration
How Agents Should Reference This
Agent prompts should:
- Always load TIER 0 skills at session start
- Load TIER 1 skills when entering their specific phase
- Load TIER 2 skills only when explicitly triggered
Referenced By
.gemini/GEMINI.md — TIER 0 at bootstrap.cursorrules — TIER 0 at bootstrap- All agent prompts — TIER 1 at phase entry
- VDD workflows — TIER 2 when invoked
1---2name: skill-phase-context3description: "Skill loading tiers: TIER 0 (always), TIER 1 (phase-triggered), TIER 2 (extended). Defines when to load which skills."4tier: 25version: 1.16---78# Phase Context Loading Protocol910This skill defines **skill loading tiers** to optimize token consumption while preserving automation capabilities.1112> [!IMPORTANT]13> **Single Source of Truth for Skill Loading Strategy.**14> Reference this skill to understand WHEN to load WHICH skills.1516## TIER 0: System Foundation — ALWAYS LOADED1718> [!CAUTION]19> **NEVER lazy-load TIER 0 skills. They enable core automation.**20> These skills MUST be available in EVERY session at bootstrap.2122| Skill | Tokens | Why Always Load |23|-------|--------|-----------------|24| `core-principles` | ~519 | Anti-hallucination rules, Stub-First, Documentation First |25| `skill-safe-commands` | ~927 | **Enables automation** — `mv`, `ls`, `git`, tests auto-run |26| `artifact-management` | ~636 | Archiving protocol, file management, dual state tracking |27| **TOTAL** | **~2,082** | **Non-negotiable system foundation** |2829### TIER 0 Loading Rule30- Load at session bootstrap (via `GEMINI.md` / `.cursorrules`)31- These skills are loaded BEFORE any phase begins32- Never remove or defer loading of TIER 0 skills3334---3536## TIER 1: Phase-Triggered — Load on Phase Entry3738These skills are phase-specific and loaded when entering the corresponding phase.3940| Phase | Skills to Load | Approx. Tokens |41|-------|----------------|----------------|42| **Analysis** | `requirements-analysis`, `skill-task-model`, `artifact-formalizer` (contract only), (`skill-archive-task` if new task) | ~3,100-4,000 |43| **Architecture** | `architecture-design`, `artifact-formalizer` (contract only), (`architecture-format-core` OR `-extended`) | ~2,850-4,200 |44| **Planning** | `planning-decision-tree`, `skill-planning-format`, `tdd-stub-first`, `artifact-formalizer` (contract only) | ~2,525 |45| **Development** | `developer-guidelines`, `documentation-standards` | ~1,100 |46| **Review** | Phase-specific `-review-checklist` skill | ~300-400 |47| **Security** | `security-audit` | ~500 |48| **VDD** | `vdd-adversarial`, (`adversarial-*` per workflow) | ~1,000-2,500 |4950### TIER 1 Loading Conditions5152**Analysis Phase:**53- `requirements-analysis` — When 02_analyst activated54- `skill-task-model` — When creating/updating TASK.md55- `skill-archive-task` — When existing TASK.md detected AND new (unrelated) task5657**Architecture Phase:**58- `architecture-design` — When 04_architect activated59- `architecture-format-core` — **Default** for most updates60- `architecture-format-extended` — Load ONLY for:61 - Creating NEW system from scratch62 - Major refactor (>3 components affected)63 - User explicitly requests "full architecture template"6465**Planning Phase:**66- `planning-decision-tree` — When 06_planner activated67- `skill-planning-format` — When creating PLAN.md68- `tdd-stub-first` — When stub creation starts6970**Development Phase:**71- `developer-guidelines` — When 08_developer activated72- `documentation-standards` — When updating docs7374**Review Phase:**75- Load the appropriate `*-review-checklist` for the current review type7677**Every authoring phase (Analysis, Architecture, Planning):**78- `artifact-formalizer` — load `references/authoring-contract.md` **before** the first sentence of79 any artifact is written. Load the SKILL.md body and the scanner only when auditing an artifact80 that already exists.81- **Why.** The contract is ~1,100 tokens; auditing an artifact afterwards costs a full re-read of82 that artifact plus the rewrite. Measured cost of the late order:83 `artifact-formalizer/references/measurement-baseline.md` §5.8485---8687## TIER 2: Extended — Load Only When Explicitly Requested8889These skills are specialized and loaded only when explicitly invoked by user or workflow.9091| Skill | Tokens | Loading Condition |92|-------|--------|-------------------|93| `architecture-format-extended` | ~3,000 | New system / major refactor / user requests full template |94| `skill-reverse-engineering` | ~1,322 | User requests "sync docs with code" / docs-code mismatch |95| `skill-update-memory` | ~1,101 | Post-development phase, .AGENTS.md updates needed |96| `skill-adversarial-security` | ~838 | VDD workflow with security focus |97| `skill-adversarial-performance` | ~946 | VDD workflow with performance focus |98| `vdd-sarcastic` | ~145 | VDD workflow with sarcastic mode |99100---101102## Integration103104### How Agents Should Reference This105106Agent prompts should:1071. Always load TIER 0 skills at session start1082. Load TIER 1 skills when entering their specific phase1093. Load TIER 2 skills only when explicitly triggered110111### Referenced By112- `.gemini/GEMINI.md` — TIER 0 at bootstrap113- `.cursorrules` — TIER 0 at bootstrap114- All agent prompts — TIER 1 at phase entry115- VDD workflows — TIER 2 when invoked
MatrixFounder