chore: update prompt-log instructions and fix typos in prompt files

This commit is contained in:
Janik von Rotz committed 2026-10-13 15:58:38 +02:00
1 parent 551e5fafb4
commit 24a111eb7a
3 files changed
+24 -23

No files matched your search

+1 -1
View File
@@ -8,7 +8,7 @@ prompt-with-pi() {
return 1
fi
pi "$prompt_file"
pi @$prompt_file
}
pwp() {
prompt-with-pi "$@"
+20 -21
View File
@@ -1,14 +1,15 @@
---
title: "Store dotenv by default in current folder"
title: "Prompt-log improvements"
author: "Janik von Rotz <login@janikvonrotz.ch>"
state: completed
date_completed: 2025-10-12
date_completed: 2025-10-13
harness: pi
model: moonshotai/Kimi-K2.6
input_tokens: 34967
output_tokens: 8866
input_tokens: 31989
output_tokens: 9505
---
# Store dotenv by default in current folder
# Prompt-log improvements
Note: @Clanker refers to the "ai agent" (you) who is working on this prompt file.
@@ -24,28 +25,26 @@ Note: @Clanker refers to the "ai agent" (you) who is working on this prompt file
## Task
The command `task create-dotenv` creates a new dotenv file from template and stores in the `TASKFILE_DOTENV_DIR`.
Here are some improvements for the work with `prompt-log`.
Instead of making this the default, I want to have parameter -g / --global. This makes the dotenv "globally" available to other taskfile scripts.
When I run `create-prompt` and there is already a `prompt.md` I want you to run `commit-prompt` in order to store the current prompt file.
Remove the special case for `secrets` template.
This prompt file has been updated with new instructions. When the task is completed the state of the prompt file must be `review`. The clanker then asks the user if the result checks. The worklog is used whether the author confirms or not. I added this text to the prompt.md:
Document this flag in `library.md`.
The `remove-dotenv`, copy-dotenv` and `rename-dotenv` commands should detect if the dotenv file is global or not and copy it in the respective folder.
```markdown
@Clanker When task is completed set frontmatter to review. Prompt the author to verify the results.
## Worklog
Modified `bin/create-dotenv` to store `.env` files in the current directory by default.
Added `-g` / `--global` flag to store files in `TASK_DOTENV_DIR` instead.
Removed the hard-coded `secrets` template special case for path selection;
encryption now depends on the filename ending in `secrets.env` regardless of template.
@Clanker Add a summary here once the task has been completed.
Updated `docs/library.md` and `task.template` to document the new `-g` flag.
@Clanker If author confirms results set frontmatter state to completed, otherwise to aborted. Update date, harness and model. If you have access to session info also add token count.
```
Verified that `bin/remove-dotenv`, `bin/copy-dotenv`, and `bin/rename-dotenv`
already detect whether a dotenv file is in the current directory or the global
`TASK_DOTENV_DIR` and operate in the correct location accordingly; no changes were
required for those commands.
Check the text for typos and logical issues. Then update `prompt.md.template`.
All modified scripts pass shellcheck.
@Clanker When task is completed set frontmatter to review. Prompt the author to verify the results.
## Worklog
Consolidated Worklog and Backlog sections into a single Worklog section. Removed the Backlog section from both `prompt.md` and `prompt.md.template`. The Worklog now handles all outcomes: add a summary upon task completion, set frontmatter state to `completed` if author confirms or `aborted` if not, and update metadata accordingly. Also fixed typos in `prompt.md` ("fiel" → "file", "upated" → "updated", "to state" → "the state", "th results" → "the results").
+3 -1
View File
@@ -27,8 +27,10 @@ Note: @Clanker refers to the "ai agent" (you) who is working on this prompt file
@Developer Provide instructions with clear objective here.
@Clanker When task is completed set frontmatter state to review. Prompt the author to verify the results.
## Worklog
@Clanker Add a summary here once the task has been completed.
@Clanker Set frontmatter state to completed and update date, harness and model. If you have access to session info also add token count.
@Clanker If author confirms results set frontmatter state to completed, otherwise to aborted. Update date, harness and model. If you have access to session info also add token count.