ace:resume-task

A command for continuing one interrupted task using its task plan, project state, and recent Git history.

In plain words
What is it for?
Resuming a task by checking its plan, involved files, verification criteria, commits, and uncommitted changes before continuing.
Why use it?
It reconstructs what was already completed and what remains, reducing the risk of repeating work after an interruption.

Command

Install

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.

agentmods
npx agentmods add commands/agricidaniel/ace-claude-code/resume-task
Clone the repo
git clone --depth 1 https://github.com/AgriciDaniel/ace-claude-code
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 445 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.00445
Opus 5 $0.00005 $0.00222
Sonnet 5 $0.00002 $0.00089
Haiku 4.5 $0.00001 $0.00044

Measured 2d ago against content hash 6efabc488c7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ace:resume-task 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.

.ace/commands/resume-task.md · 99 lines

What it actually says

Used when execution stopped mid-task (not between tasks).

Required: @.ace/planning/STATE.md PLAN.md for the specified plan

1. Parse Task ID

if $ARGUMENTS is empty or invalid format:
    Error: "Specify task: /ace:resume-task 01-02-1"

Extract: phase, plan, task number

2. Load Task Context

Read PLAN.md for that task:

  • Task description
  • Zone assignment
  • Files involved
  • Verification criteria

3. Check Git State

git status --porcelain
git log --oneline -5

Determine:

  • What commits exist for this plan
  • What files have uncommitted changes
  • What work was already done

4. Display Resume Context

+==============================================================+
|                    RESUME TASK                               |
+==============================================================+

Task: [task_id] - [task name]
Zone: [ALPHA/BETA/GAMMA]

Previous Work:
- [Files already created/modified]
- [Commits already made]

Remaining:
- [What still needs to be done]

+==============================================================+

5. Resume Execution

Spawn Team Lead for just this task:

  • Provide context of what's already done
  • Complete remaining work
  • Commit when done

6. Update State

After completion:

  • Update STATE.md
  • Continue with remaining tasks if any

<success_criteria>

  • Task context loaded
  • Previous work identified
  • Task completed
  • Properly committed </success_criteria>
Changes

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.

  1. 2d ago First seen · 99 lines · 10 tokens per session scan A 6efabc488c7d

Subscribe to this mod's changes

ace:resume-task 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 445 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.