ace:recover-execution

ace:recover-execution is a command for coding agents from AgriciDaniel/ace-claude-code. It costs 12 tokens per session (1,665 once invoked), scanned A, original, MIT.

A recovery command for projects that stopped partway through a multi-step coding plan. It compares the plan with the saved state and Git history to determine what finished and what failed.

In plain words
What is it for?
Use it to read the project state, inspect uncommitted changes and recent commits, check for a summary, and offer ways to resume failed tasks.
Why use it?
It removes guesswork after an interrupted execution, especially when some tasks or commits are already complete. It helps restore a consistent working context before continuing.

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/recover-execution
Clone the repo
git clone --depth 1 https://github.com/AgriciDaniel/ace-claude-code

Wrote 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.

agentmods badge for ace:recover-execution

README.md
[![agentmods](https://agentmods.dev/badge/commands/agricidaniel/ace-claude-code/recover-execution.svg)](https://agentmods.dev/commands/agricidaniel/ace-claude-code/recover-execution)
Your own site
<a href="https://agentmods.dev/commands/agricidaniel/ace-claude-code/recover-execution"><img src="https://agentmods.dev/badge/commands/agricidaniel/ace-claude-code/recover-execution.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,665 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 $0.00012 $0.01665
Opus 5 $0.00006 $0.00833
Sonnet 5 $0.00002 $0.00333
Haiku 4.5 $0.00001 $0.00167

Measured 4d ago against content hash 2af46f994fa7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ace:recover-execution 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 4d 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/recover-execution.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identifies completed vs failed tasks, offers recovery options, and restores the execution context to a consistent state.

Required: @.ace/planning/STATE.md @.ace/config.json

Load: Current PLAN.md from phases/ Git status and log for partial commits

1. Detect Current State

+==============================================================+
|                    EXECUTION RECOVERY                        |
+==============================================================+

Analyzing execution state...

Run the following checks:

  1. Read STATE.md for current plan info
  2. Run git status to check for uncommitted changes
  3. Run git log --oneline -10 to find recent commits
  4. Check if SUMMARY.md exists (partial or complete)

2. Identify Completed Tasks

Parse the PLAN.md and cross-reference with git log:

EXECUTION STATE ANALYSIS:

Plan: [plan_id] - [plan name]
Started: [timestamp from STATE.md]

TASK STATUS:
+--------+------------------+----------+------------+
| Zone   | Task             | Status   | Commit     |
+--------+------------------+----------+------------+
| ALPHA  | Create models    | COMPLETE | abc1234    |
| BETA   | Add services     | FAILED   | -          |
| GAMMA  | Create routes    | PENDING  | -          |
+--------+------------------+----------+------------+

UNCOMMITTED CHANGES:
- src/services/auth.ts (modified)
- src/services/user.ts (new file)

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

3. Diagnose Failure

Identify failure type:

  • Partial commit: Some files staged/modified but not committed
  • Quality gate failure: Build/lint/test failed
  • Zone conflict: Files modified outside assigned zone
  • Timeout: Agent timed out mid-task
  • Unknown: Other failure
FAILURE DIAGNOSIS:

Type: [failure type]
Zone: BETA
Task: Add services

Details:
[Error message or symptoms]

Affected Files:
- src/services/auth.ts
- src/services/user.ts

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

Read the full file on GitHub · 312 lines

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. 4d ago First seen · 312 lines · 12 tokens per session scan A 2af46f994fa7

Subscribe to this mod's changes

ace:recover-execution 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 1,665 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.