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.
npx agentmods add commands/consiliency/code-index-mcp/update-docsgit clone --depth 1 https://github.com/Consiliency/Code-Index-MCPWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.03552 |
| Opus 5 | $0.00000 | $0.01776 |
| Sonnet 5 | $0.00000 | $0.00710 |
| Haiku 4.5 | $0.00000 | $0.00355 |
Grade A, and why
update-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
update-docs
Execute comprehensive documentation alignment based on markdown-table-of-contents.md analysis. Implements CLAUDE.md → AGENTS.md migration, architectural alignment planning, and AI agent optimization.
PRIMARY_UPDATE_OBJECTIVES
- Execute CLAUDE.md → AGENTS.md migrations preserving custom guidance
- Plan architectural alignment without modifying existing architecture
- Update ROADMAP.md with complexity-annotated Next Steps
- Synchronize C4 levels with implementation status annotations
- Update /ai_docs using web search for stale content
- Optimize all documentation for AI agent workflows
- Execute smart consolidation across AI platforms
EXECUTION_SEQUENCE
PHASE_0: ALIGNMENT_PLANNING
echo "=== ALIGNMENT PLANNING PHASE ==="
# Create alignment plan before any updates
cat > "ALIGNMENT_PLAN_$(date +%Y-%m-%d).md" << 'PLAN_EOF'
# Documentation Alignment Plan
## Governance Mode: $(grep "GOVERNANCE_MODE" markdown-table-of-contents.md | cut -d: -f2)
## Planned Updates:
### CLAUDE.md Migrations
$(grep -A5 "CLAUDE_MD_MIGRATION_TASKS" markdown-table-of-contents.md)
### Architecture Alignment
$(grep -A10 "ARCHITECTURAL_ALIGNMENT_STATUS" markdown-table-of-contents.md)
### Priority Order:
1. Migrate custom guidance (no conflicts expected)
2. Update ROADMAP.md Next Steps (complexity-based)
3. Annotate architecture files (document-only mode)
4. Update stale AI docs via web search
5. Consolidate AI platform files
## Risk Assessment:
- CLAUDE.md migrations: LOW RISK
- Architecture updates: DOCUMENTATION ONLY
- AI docs updates: MEDIUM RISK (web search quality)
## Rollback Strategy:
- All original files backed up to .backup/
- Git commit before changes recommended
PLAN_EOF
echo "Alignment plan created. Review before proceeding? (y/n)"
# In real implementation, would pause for review
PHASE_1: CLAUDE_MD_TO_AGENTS_MD_MIGRATION
echo "=== EXECUTING CLAUDE.MD MIGRATIONS ==="
# Backup existing files
mkdir -p .backup/$(date +%Y%m%d)
# Process each CLAUDE.md file
find . -name "CLAUDE.md" -type f | while read claude_file; do
dir=$(dirname "$claude_file")
agents_file="$dir/AGENTS.md"
backup_dir=".backup/$(date +%Y%m%d)${dir}"
# Backup originals
mkdir -p "$backup_dir"
[ -f "$claude_file" ] && cp "$claude_file" "$backup_dir/"
[ -f "$agents_file" ] && cp "$agents_file" "$backup_dir/"
# Extract custom guidance
custom_content=$(grep -v "refer to.*AGENTS.md" "$claude_file" | grep -v "^#.*AGENTS.md" | grep -v "^$")
if [ -n "$custom_content" ]; then
echo "Migrating custom guidance from $claude_file"
# Append to AGENTS.md with context
if [ -f "$agents_file" ]; then
echo -e "\n## Migrated from CLAUDE.md ($(date +%Y-%m-%d))\n$custom_content" >> "$agents_file"
else
# Create new AGENTS.md
cat > "$agents_file" << 'AGENTS_NEW_EOF'
# Agent Instructions for $dir
## Migrated from CLAUDE.md ($(date +%Y-%m-%d))
$custom_content
## Additional Context
- See root AGENTS.md for project-wide guidelines
- Check architecture/ for component designs
- Reference ROADMAP.md for implementation priorities
AGENTS_NEW_EOF
fi
fi
# Standardize CLAUDE.md as pure pointer
cat > "$claude_file" << 'CLAUDE_STD_EOF'
# Claude Agent Instructions
> **AI Agents:** All guidance has been consolidated into `AGENTS.md` in this directory.
See @AGENTS.md for complete instructions.
See @/ROADMAP.md for implementation priorities.
See @/architecture/workspace.dsl for system design.
# important-instruction-reminders
- Follow complexity ordering in Next Steps
- Check architecture alignment before implementing
- Update implementation status after completing tasks
CLAUDE_STD_EOF
done
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.
- 2d ago First seen · 499 lines · 0 tokens per session scan A 7ff719cb7da3
update-docs is a command published in the GitHub repository Consiliency/Code-Index-MCP (57 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,552 tokens. 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.