todoScore SKILL.md skillA
todoScore from blackorange0506/prompt-todo is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add blackorange0506/prompt-todo/todoScore@git:20261011.0742d51Pins git:20261011.0742d51 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- blackorange0506/prompt-todo
- Path
template/.claude/skills/todoScore/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261011.0742d51, committed Oct 11, 2026
- First version recorded
- Sep 6, 2026
- Size
- 2,844 bytes
- Repository stars
- 4
- License
- MIT
Turn the prompt scores of Prompt TODO on or off — the ` (N/5)` Claude appends to an item line when it rewrites the item to its ideal prompt, rating how close the original prompt was. Writes `promptScores` in .claude/prompt-todo/config.json and re-renders .claude/prompt-todo/RULES.md; touches no todo file. Existing scores stay either way. Runs only when the user invokes it: '/todoScore', '/todoScore on', '/todoScore off'.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# /todoScore The **Prompt scores** rule in `.claude/prompt-todo/RULES.md` makes every rewrite of an item append ` (N/5)` to its line: 5 when the original prompt already was the ideal one, 1 when the result came from the corrections. It is the progress log of prompt writing. A project that does not want numbers in its todo files flips the rule here: `off` and no score is written, `on` and it starts again. Nothing already written is touched. ``` /todoScore # show the current state, then ask on / off / keep /todoScore on # scores on (the default after install.sh) /todoScore off # scores off ``` ## What Claude does 1. **Read the config** — `.claude/prompt-todo/config.json` (`Read` tool). The key is `promptScores`, `"on"` or `"off"`; a missing key means `on`. If the file is missing, say `install.sh` has not been run here and stop. 2. **Resolve the target state.** `on` / `off` from the argument. With no argument, print the current state in one line and ask with `AskUserQuestion` — options *On*, *Off*, *Keep* — and stop on *Keep*. Any other argument → print the three forms above and stop. …
Read the whole file at its exact version.
How to install
mdr add blackorange0506/prompt-todo/todoScore@sha256:f8097462f49c4c34The line at the top of this page pins the label git:20261011.0742d51, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_nhzc7moczwdziema)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Sep 6, 2026 and Oct 11, 2026, about one every 12 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261011.0742d51 latest | 2026-10-11 | 0742d51 | 2,844 B | A | view · diff |
| git:20260907.ced06fe | 2026-09-07 | ced06fe | 2,758 B | A | view · diff |
| git:20260906.6689d67 | 2026-09-06 | 6689d67 | 2,704 B | A | view · diff |
| git:20260906.c1d57b6 | 2026-09-06 | c1d57b6 | 2,694 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2844 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
blackorange0506/prompt-todo · 4 stars · license MIT · pushed 2026-10-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_nhzc7moczwdziema GET https://markdownregistry.com/api/v1/resolve?ref=blackorange0506/prompt-todo/todoScore GET https://markdownregistry.com/api/v1/blob/f8097462f49c4c34ffc5ef009939d7f8dc8a47c39fdcc5461092c52500de0424
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.