skill-phase-context

A guide for deciding which skills an agent should load at different stages of a task. A skill is a set of instructions that helps an agent perform a particular kind of work.

In plain words
What is it for?
Use it to define always-loaded skills, stage-specific skills, and extended skills for multi-step agent workflows.
Why use it?
It keeps essential instructions available while delaying less relevant material until it is needed, which reduces unnecessary context.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/matrixfounder/agentic-development/skill-phase-context
Any agent
npx skills add MatrixFounder/Agentic-development --skill skill-phase-context
Clone the repo
git clone --depth 1 https://github.com/MatrixFounder/Agentic-development

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,232 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.01232
Opus 5 $0.00019 $0.00616
Sonnet 5 $0.00008 $0.00246
Haiku 4.5 $0.00004 $0.00123

Measured 2d ago against content hash 097e0a38e762, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-phase-context scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agent/skills/skill-phase-context/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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 automationmv, 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

Read the full file on GitHub · 115 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 115 lines · 38 tokens per session scan A 097e0a38e762

Subscribe to this mod's changes

skill-phase-context is a skill published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,232 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

claude-to-deerflow

Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research/analysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models/skills/agents in DeerFlow, manage DeerFlow memory, upload files to…

bytedance/deer-flow · 111 tokens

find-skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

bytedance/deer-flow · 67 tokens

skill-reviewer

Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.

bytedance/deer-flow · 38 tokens

zeroclaw

Help users operate and interact with their ZeroClaw agent instance — through both the CLI (zeroclaw commands) and the REST/WebSocket gateway API. Use this skill whenever the user wants to: send messages to ZeroClaw, manage memory or cron jobs, check system status, configure channels or providers, hit the gateway API…

zeroclaw-labs/zeroclaw · 167 tokens

build-monetized-app

Use when the task is building a new app on Eliza Cloud that earns money — chat apps, agent apps, MCP-backed tools, anything that calls the cloud's chat/messages/inference endpoints on behalf of users. Covers app registration, container deploy, markup configuration, affiliate header, app charge requests, x402 payment…

elizaOS/eliza · 126 tokens

extension-creator

Create, scaffold, customize, validate, and locally test Qwen Code extensions. Use when the user wants a new Qwen Code extension, needs help choosing an extension template, wants to add QWEN.md context, commands, skills, agents, MCP servers, settings, hooks, channels, or LSP servers, or asks how to link and test an…

QwenLM/qwen-code · 96 tokens