Claude-skill-registry inject

Inject relevant knowledge into session context from .agents/ artifacts. Triggers: "inject knowledge", "recall context", SessionStart hook.

install
source · Clone the upstream repo
git clone https://github.com/majiayu000/claude-skill-registry
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/inject" ~/.claude/skills/majiayu000-claude-skill-registry-inject && rm -rf "$T"
manifest: skills/data/inject/SKILL.md
source content

Inject Skill

Typically runs automatically via SessionStart hook.

Inject relevant prior knowledge into the current session.

How It Works

The SessionStart hook runs:

ao inject --apply-decay --format markdown --max-tokens 1000

This searches for relevant knowledge and injects it into context.

Manual Execution

Given

/inject [topic]
:

Step 1: Search for Relevant Knowledge

With ao CLI:

ao inject --context "<topic>" --format markdown --max-tokens 1000

Without ao CLI, search manually:

# Recent learnings
ls -lt .agents/learnings/ | head -5

# Recent patterns
ls -lt .agents/patterns/ | head -5

# Recent research
ls -lt .agents/research/ | head -5

Step 2: Read Relevant Files

Use the Read tool to load the most relevant artifacts based on topic.

Step 3: Summarize for Context

Present the injected knowledge:

  • Key learnings relevant to current work
  • Patterns that may apply
  • Recent research on related topics

Knowledge Sources

SourceLocationPriority
Learnings
.agents/learnings/
High
Patterns
.agents/patterns/
High
Research
.agents/research/
Medium
Retros
.agents/retros/
Medium

Decay Model

Knowledge relevance decays over time (~17%/week). More recent learnings are weighted higher.

Key Rules

  • Runs automatically - usually via hook
  • Context-aware - filters by current directory/topic
  • Token-budgeted - respects max-tokens limit
  • Recency-weighted - newer knowledge prioritized