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/resume-workgit clone --depth 1 https://github.com/AgriciDaniel/ace-claude-codeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/agricidaniel/ace-claude-code/resume-work)<a href="https://agentmods.dev/commands/agricidaniel/ace-claude-code/resume-work"><img src="https://agentmods.dev/badge/commands/agricidaniel/ace-claude-code/resume-work.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00010 | $0.00496 |
| Opus 5 | $0.00005 | $0.00248 |
| Sonnet 5 | $0.00002 | $0.00099 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
ace:resume-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 3d 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.
What it actually says
This is the primary session restoration command.
Check for: .ace/planning/.continue-here*.md
1. Load State
Read STATE.md to understand:
- Current position
- Last activity
- Resume file path (if any)
2. Check for Continue-Here File
glob: .ace/planning/.continue-here*.md
If found:
- Read the most recent one
- Load context from it
3. Display Restoration
+==============================================================+
| SESSION RESTORED |
+==============================================================+
Welcome back!
Last Session: [YYYY-MM-DD HH:MM]
Duration Since: [X] hours/days
## Current Position
Phase: [X] of [Y] ([Phase Name])
Plan: [A] of [B]
Status: [Status from STATE.md]
Progress: [##########..........] 50%
## Where You Left Off
[Content from continue-here file]
## Next Actions
1. [From continue-here or inferred]
2. [Following step]
+==============================================================+
4. Suggest Next Command
Based on status:
| Status | Suggestion |
|---|---|
| Ready to plan | /ace:plan-phase [N] |
| Ready to execute | /ace:execute-plan |
| In progress (task) | /ace:resume-task [id] |
| Needs verification | /ace:verify-work |
SUGGESTED NEXT:
/ace:[appropriate-command]
Or run /ace:progress for full status.
+==============================================================+
5. Clean Up (Optional)
If work resumed successfully, offer to archive continue-here file:
- Move to
.ace/state/archived/ - Or delete
<success_criteria>
- STATE.md loaded
- Continue-here file found and read (if exists)
- Context displayed to user
- Appropriate next action suggested </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.
- 3d ago First seen · 110 lines · 10 tokens per session scan A b788f08dd490
ace:resume-work is a command published in the GitHub repository AgriciDaniel/ace-claude-code (24 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 496 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.