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/pause-workgit 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 | $0.00012 | $0.00556 |
| Opus 5 | $0.00006 | $0.00278 |
| Sonnet 5 | $0.00002 | $0.00111 |
| Haiku 4.5 | $0.00001 | $0.00056 |
Grade A, and why
ace:pause-work 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Captures current state and context for the next session.
Check for:
- Active plan in progress
- Uncommitted changes
1. Capture Current State
Read STATE.md and determine:
- Current phase and plan
- Last completed task
- Any in-progress work
2. Check for Uncommitted Changes
git status --porcelain
If uncommitted changes exist:
- List them
- Ask if they should be committed or stashed
3. Create Continue-Here Document
Write to .ace/planning/.continue-here-{timestamp}.md:
# Continue Here
**Paused:** [YYYY-MM-DD HH:MM]
## Current Position
Phase: [X] of [Y] ([Phase Name])
Plan: [A] of [B]
Task: [Last completed / In progress]
## What Was Happening
[Description of current work state]
## Uncommitted Changes
[List of uncommitted files, if any]
## Next Actions
1. [Immediate next step]
2. [Following step]
## Context Notes
[Any important context for resumption]
## To Resume
Run: /ace:resume-work
4. Update STATE.md
Set:
- Session continuity: paused
- Resume file: path to continue-here
5. Git Commit (WIP)
If there's uncommitted planning work:
git add .ace/planning/
git commit -m "wip: [phase-name] paused at task [X]/[Y]
[Brief description]
"
6. Confirmation
+==============================================================+
| WORK PAUSED |
+==============================================================+
Handoff created: .ace/planning/.continue-here-[timestamp].md
Current State:
Phase: [X] - [Name]
Plan: [A] of [B]
Progress: [##########..........] 50%
To continue later:
/ace:resume-work
+==============================================================+
<success_criteria>
- Continue-here document created
- STATE.md updated with resume file path
- WIP committed if applicable
- User informed how to resume </success_criteria>
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 · 128 lines · 12 tokens per session scan A 4ce41e4eba35
ace:pause-work is a command published in the GitHub repository AgriciDaniel/ace-claude-code (24 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 556 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.
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.