A prompt for automation that can report its own failure - #39
Merged
Conversation
Upstream #43 asked for prompts across automation, error handling, documentation and architecture summary. Open since 2025-07-21. This is the fourth and last of them, and every category that list asked for is now answered here. Written from scratch; that repository carries no licence and only the demand is free to answer. Its thesis is this machine's own scar tissue: the failure that matters is not a script that breaks but one that succeeds without doing anything. A gate on the left of a pipe, a tool that exits 0 while failing, a truncated listing concluded from, a completion marker matching a previous run. Signed-off-by: Melbin J Paulose <melbinjpaulose@gmail.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The last of the four categories asked for in
google-labs-code/jules-awesome-list#43, open since 2025-07-21. With it, every category that list asked for and never merged is answered here: documentation, database, error handling, architecture summary, translated docs, automation.Written from scratch. That repository carries no licence, so its wording belongs to its author and only the demand is free to answer.
The request was for automating a workflow with a shell script, and the naive shape of that is what
_prompts/task_automate_a_workflow.mdargues with. The failure worth designing against is not a script that breaks, it is one that succeeds without doing anything, and that is invisible by construction: the command exits0, the output looks complete, and nothing says there was more.verify | tail -1 && commitruns the commit whenverifyfailed, because a pipeline takes the exit status of its last command.So the prompt has the agent find the workflow in the history rather than take it on description, verify each step by its effect rather than its exit code, make it safe to run twice and safe to interrupt, and then break it on purpose and report what it did.
25 prompts, 25 guide entries, workflow agrees,
_config.ymlparses.