decision-journal SKILL.md skillA
This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.
decision-journal from narendawar/narens-claude-toolkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add narendawar/narens-claude-toolkit/decision-journal@git:20261001.6851e1fPins git:20261001.6851e1f in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- narendawar/narens-claude-toolkit
- Path
plugins/decision-journal/skills/decision-journal/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261001.6851e1f, committed Oct 1, 2026
- First version recorded
- Oct 1, 2026
- Size
- 4,978 bytes
- Repository stars
- 4
- License
- MIT
Use when the user wants to log a prediction or estimate about a dev or project decision, grade past predictions, or see how calibrated they are (for example 'log a prediction', 'grade my predictions', 'how calibrated am I?').
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
# Decision Journal ## Overview Keep a log of the user's predictions about dev and project decisions, grade them when outcomes are known, and show where they are overconfident. A script does all the writing and arithmetic so the numbers are always right; you do the conversation. It runs only when the user asks. Never log, grade, or offer to log unprompted: an offhand "this should take a few hours" is not a request. ## The script `scripts/journal.py` in this skill's directory (use the base directory shown when the skill loads). It needs Python 3 and the standard library only. The log is `~/.claude/decision-journal.jsonl`, one JSON object per line. Commands: - `python journal.py add --type claim --text "..." --confidence 70 [--know-by YYYY-MM-DD] [--tag a,b]` - `python journal.py add --type estimate --text "..." --unit hours --estimate 2 [--range-low 1.5 --range-high 4] [--know-by YYYY-MM-DD] [--tag a,b]` - `python journal.py list [--open | --due]` (prints JSON) - `python journal.py grade ID --outcome yes|no` or `grade ID --actual NUMBER` [--note "..."] [--force] - `python journal.py stats [--tag T]` …
Read the whole file at its exact version.
How to install
mdr add narendawar/narens-claude-toolkit/decision-journal@sha256:beb354c3ae330566The line at the top of this page pins the label git:20261001.6851e1f, 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_hlj2qicjkwa7nvqj)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, all committed on Oct 1, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261001.6851e1f latest | 2026-10-01 | 6851e1f | 4,978 B | A | view · diff |
| git:20261001.15ebe60 | 2026-10-01 | 15ebe60 | 4,940 B | A | view · diff |
| git:20261001.7d215e6 | 2026-10-01 | 7d215e6 | 4,724 B | A | view · diff |
| git:20261001.23c1258 | 2026-10-01 | 23c1258 | 577 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 (4978 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
narendawar/narens-claude-toolkit · 4 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hlj2qicjkwa7nvqj GET https://markdownregistry.com/api/v1/resolve?ref=narendawar/narens-claude-toolkit/decision-journal GET https://markdownregistry.com/api/v1/blob/beb354c3ae330566b61dd9fb69040061f47cd66c670c85d8dee4465914f0d91c
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.
More from narendawar/narens-claude-toolkit
Every file in narendawar/narens-claude-toolkit