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/validate-plangit 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 | $0.00011 | $0.02000 |
| Opus 5 | $0.00005 | $0.01000 |
| Sonnet 5 | $0.00002 | $0.00400 |
| Haiku 4.5 | $0.00001 | $0.00200 |
Grade A, and why
ace:validate-plan 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Catches errors early to prevent execution failures, ensuring all required fields exist, zones are valid, and there are no conflicts.
Required: @.ace/planning/STATE.md (if no path provided) @.ace/project-types.json
Load: Target PLAN.md file
1. Locate Plan File
if $ARGUMENTS provided:
plan_path = $ARGUMENTS
else:
Read STATE.md for current plan path
if plan not found:
Error: "No plan file found. Provide path or run /ace:plan-phase first"
2. Parse Plan Structure
Read the PLAN.md and extract:
- Header metadata (Plan ID, Phase, Name)
- Task blocks
- Checkpoint definitions (if any)
+==============================================================+
| PLAN VALIDATION |
+==============================================================+
Plan: [plan_path]
Parsing structure...
3. Validate Required Fields
For each task block, check required fields:
Required Task Fields
| Field | Required | Format |
|---|---|---|
| Zone | YES | ALPHA, BETA, or GAMMA |
| Files | YES | List of file patterns |
| Action | YES | Description of what to do |
| Verify | YES | How to verify completion |
| Done when | YES | Completion criteria |
Validation Process
FIELD VALIDATION:
Task 1: "Create user model"
Line 15: [*] Zone: ALPHA
Line 16: [*] Files: src/models/user.ts
Line 17: [*] Action: Present
Line 20: [*] Verify: Present
Line 23: [*] Done when: Present
Task 2: "Add auth service"
Line 30: [*] Zone: BETA
Line 31: [X] Files: MISSING
Line 32: [*] Action: Present
Line 35: [X] Verify: MISSING
Line 38: [*] Done when: Present
+==============================================================+
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 · 351 lines · 11 tokens per session scan A 6c236766dcd3
ace:validate-plan is a command published in the GitHub repository AgriciDaniel/ace-claude-code (24 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 2,000 once invoked, about $0.0001 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.
test
Generate comprehensive tests for a file or function.
review
Review code for best practices and issues.
fix-issue
Analyze and fix a GitHub issue.
migrate
Create migration plan for upgrade.