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/agricidaniel/ace-claude-code/helpgit clone --depth 1 https://github.com/AgriciDaniel/ace-claude-codeWhat 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 | $0.00008 | $0.01414 |
| Opus 5 | $0.00004 | $0.00707 |
| Sonnet 5 | $0.00002 | $0.00283 |
| Haiku 4.5 | $0.00001 | $0.00141 |
Grade A, and why
ace:help 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Display:
+==============================================================+
| ACE HELP |
+==============================================================+
Ace - Unified Multi-Agent Orchestration System
+--------------------------------------------------------------+
| QUICK REFERENCE |
+--------------------------------------------------------------+
QUICK START:
/ace:init # Fast setup (or new-project + create-roadmap)
/ace:plan-phase 1 # Plan first phase
/ace:execute-plan # Run the plan
/ace:verify-work # Test results
COMMON WORKFLOWS:
/ace:progress # Where am I?
/ace:list-phases # See all phases
/ace:show-plan # View current plan
/ace:resume-work # Continue after break
+--------------------------------------------------------------+
| PROJECT LIFECYCLE (4) |
+--------------------------------------------------------------+
/ace:new-project [name]
Initialize project with PROJECT.md
Creates: .ace/planning/PROJECT.md
/ace:create-roadmap
Build ROADMAP.md and STATE.md
Requires: PROJECT.md exists
/ace:map-codebase [area]
Analyze existing code (7 documents)
Creates: .ace/planning/codebase/
Use for: Brownfield projects
/ace:init
Fast project setup (combines new-project + create-roadmap)
For quick starts without detailed planning
+--------------------------------------------------------------+
| PHASE MANAGEMENT (7) |
+--------------------------------------------------------------+
/ace:plan-phase [N]
Create PLAN.md for phase N
Max 3 tasks per plan
/ace:execute-plan [path]
Run current plan with parallel Team Leads
Creates atomic commits per task
/ace:add-phase
Append new phase to roadmap
/ace:insert-phase [N]
Insert urgent phase at position N
/ace:remove-phase [N]
Remove phase N from roadmap
/ace:discuss-phase [N]
Pre-planning context gathering
Use before plan-phase for complex phases
/ace:research-phase [N]
Deep ecosystem research
Use for phases needing external knowledge
+--------------------------------------------------------------+
| VALIDATION (3) |
+--------------------------------------------------------------+
/ace:validate-plan [path]
Validate PLAN.md before execution
Checks zone conflicts, file patterns, dependencies
/ace:validate-zones
Verify zone definitions match project type
Checks for overlapping file patterns
/ace:recover-execution [plan_id]
Recover from failed or interrupted execution
Identifies incomplete tasks and resumes
+--------------------------------------------------------------+
| PROGRESS & DISPLAY (4) |
+--------------------------------------------------------------+
/ace:progress
Show status and suggest next steps
Alias: "Ace status"
/ace:status
Quick status check (alias for progress)
/ace:list-phases
Display all phases at a glance
Shows progress, dependencies, statistics
/ace:show-plan [plan_id]
Display current plan without executing
Visual task distribution and details
+--------------------------------------------------------------+
| VERIFICATION (3) |
+--------------------------------------------------------------+
/ace:verify-work [plan_id]
User acceptance testing
Captures issues for fix planning
/ace:plan-fix [plan_id]
Plan fixes for UAT issues
Creates fix plan from UAT-ISSUES.md
/ace:consider-issues
Review deferred issues from ISSUES.md
Decide which to address in next plan
+--------------------------------------------------------------+
| SESSION MANAGEMENT (3) |
+--------------------------------------------------------------+
/ace:pause-work
Create handoff document
Saves context for later resume
/ace:resume-work
Restore from last session
Alias: "Ace resume"
/ace:resume-task [id]
Resume specific interrupted task
For targeted task recovery
+--------------------------------------------------------------+
| CONFIGURATION (2) |
+--------------------------------------------------------------+
/ace:config [key] [value]
View or modify Ace settings
Examples: config workflow.mode yolo
/ace:help
Show this help (you're here!)
+--------------------------------------------------------------+
| COMMAND COUNT: 26 |
+--------------------------------------------------------------+
+==============================================================+
| WORKFLOWS |
+==============================================================+
NEW PROJECT (Greenfield):
1. /ace:new-project "My App"
2. /ace:create-roadmap
3. /ace:plan-phase 1
4. /ace:execute-plan
5. /ace:verify-work
EXISTING PROJECT (Brownfield):
1. /ace:map-codebase
2. /ace:new-project "My App"
3. Continue as greenfield...
FAST START:
1. /ace:init
2. /ace:plan-phase 1
3. /ace:execute-plan
RESUME SESSION:
/ace:progress # See where you are
/ace:resume-work # Restore context
PHASE ITERATION:
/ace:list-phases # Overview
/ace:plan-phase [N] # Plan
/ace:show-plan # Review
/ace:execute-plan # Execute
/ace:verify-work # Test
FIX ISSUES:
/ace:verify-work # Find issues
/ace:plan-fix # Plan fixes
/ace:execute-plan # Apply fixes
+==============================================================+
| LEGACY ACTIVATION |
+==============================================================+
These also work:
"Ace" - Auto-detect and start
"Ace [type]" - Start with project type
"Ace status" - Show progress
"Ace resume" - Resume work
+==============================================================+
| ARCHITECTURE |
+==============================================================+
ORCHESTRATOR
|
+---------------+---------------+
| | |
ALPHA BETA GAMMA
Lead Lead Lead
| | |
mini mini mini
agents agents agents
Team Leads execute in parallel.
Each commits atomically to their zone.
Main context stays lean (~5% usage).
+==============================================================+
| MORE INFO |
+==============================================================+
Documentation:
.ace/SKILL.md Full system documentation
.ace/config.json Configuration settings
.ace/commands/*.md Individual command definitions
.ace/templates/ Document templates
+==============================================================+
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 · 251 lines · 8 tokens per session scan A a8da0af85915
ace:help is a command published in the GitHub repository AgriciDaniel/ace-claude-code (24 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 1,414 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
canvas
AI-orchestrated visual canvas production — create, populate, layout, present, generate, and export Obsidian canvases.
document
Generate documentation for code.
review
Review code for best practices and issues.
test
Generate comprehensive tests for a file or function.
fix-issue
Analyze and fix a GitHub issue.
migrate
Create migration plan for upgrade.