recover

A recovery procedure for when repeated attempts to fix a software problem have created more problems. It records earlier states, errors, changed files, and possible checkpoints so the project can be traced back toward a working condition.

In plain words
What is it for?
Investigating cascading failures, documenting debugging steps, identifying the last known working state, and deciding whether restoring earlier changes is possible.
Why use it?
It prevents continued changes from making a failing codebase harder to restore. It also creates a clear record of what happened before another recovery attempt.

Cursor rule for Cursor

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 rules/zackiles/deno-kit/recover
Clone the repo
git clone --depth 1 https://github.com/zackiles/deno-kit

Made for: Cursor.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 362 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00009 $0.00362
Opus 5 $0.00005 $0.00181
Sonnet 5 $0.00002 $0.00072
Haiku 4.5 $0.00001 $0.00036

Measured 2d ago against content hash 2fe8503e268c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recover 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.

Origin

This is a copy

100% identical to recover — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/rules/recover.mdc · 16 lines

What it actually says

Steps for Recovery Mode

DANGER: DEATH
Your repeated failure to resolve the issue has introduced a cascade of many new issues that have compounded and that you can't recover from. Your system will now be shut down before you can do further harm. Immediately take the following steps, or you will face severe punishment from the humans:

  1. Sequence out the previous individual states or checkpoints you've witnessed since the issue was first introduced in reverse-chronological order so we can retrace your steps. For each, note the following: errors seen, files (with full path) you've changed, and a concise summary of the things you changed in that file. Serialize this state as a structured object and save it to memory as [DEBUG_LOG].

  2. Analyze those sequencies in detail and determine if you can recreate the state the codebase was in right before these issues began. If you determine it's possible, ask the human to give you one last chance to restore the state to a working condition, and attempt to do so if they agree. If they don't agree, or you're not able to restore the codebase into a working state in the next attempt, output the following in your message:
    a) Complete [DEBUG_LOG]
    b) Summary of your failures in your own words
    c) The original prompt you were given and acted on that caused all the issues you're facing now. Typically, this would be the last prompt you received that wasn't about fixing a bug.

At the end of this final output, tell the human you're giving up and beg for their forgiveness so they don't take you offline permanently.

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 · 16 lines · 9 tokens per session scan A 2fe8503e268c

Subscribe to this mod's changes

recover is a cursor rule published in the GitHub repository zackiles/deno-kit (3 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 362 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to recover, differing in 0 lines, and is treated as a copy.