Ledger
Query or maintain the persistent idea ledger and pitfall priors. Use for "check the ledger", "what does my ledger say", "have I tried this before", "my pitfalls", "update my priors", or before starting any new project. Read-mostly; writes go through idea-killer verdicts or explicit user requests.From its SKILL.md
npx -y skills add DepthWorks/idea-killer --skill ledgerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.7 KB, 363 tokens by cl100k_base, as published. Nobody here has run it
Ledger
The ledger is the user's auditable decision memory. Resolve its directory in
this order: $IDEA_LEDGER_DIR if set, else ~/.claude/ledger/.
IDEA-LEDGER.md- every idea evaluated, with verdict, failure tags, and re-entry triggers.PITFALLS.md- standing priors: failure classes with evidence tallies, plus recognition rules.
If the files do not exist, offer to initialize them from the plugin's
ledger-template/.
Answering queries
- Read both files.
- For "have I tried X" - match on the idea, its failure tags, AND its shape (same buyer, same wedge, same distribution problem). A new coat of paint on a killed shape is the same idea.
- For pattern questions - report tag tallies and Standing Priors verbatim, then interpret. Never soften a prior to be agreeable.
Maintenance rules
- New entries are appended by the idea-killer skill; do not duplicate.
- 3 KILLs sharing a tag -> promote the tag to a Standing Prior in PITFALLS.md (with the three entry ids as evidence).
- A prior can be RETIRED only by contrary external evidence (a GO that survived contact with paying users), never by argument. Record the retirement, do not delete the history.
- PARK entries: when their trigger fires, they re-enter through idea-killer, not straight to GO.
- Convert relative dates to absolute. ASCII only (no em-dashes).
- Remind the user to commit ledger changes; an uncommitted ledger is not auditable.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most finance skills give in 363 tokens
Counted across 469 of the 469 authors here whose files we hold, read 2026-08-07
- Extract date vendor amount and descriptionin 15 of 469, across 3 files
- Scan folder for invoice filesin 14 of 469, across 2 files
- Rename files to standard formatin 14 of 469, across 2 files
- Show organization plan before movingin 14 of 469, across 2 files
- Generate summary CSVin 14 of 469, across 2 files
- Organize files by categoryin 13 of 469, across 1 file
- Preserve original filesin 13 of 469, across 1 file
- Flag files missing critical infoin 13 of 469, across 1 file
- Produce the requested output filein 9 of 469, across 4 files
- Build best, base, and worst case scenariosin 9 of 469, across 5 files
- Implement backoff if rate limit errors occurin 8 of 469, across 3 files
- Determine the weighted average cost of capitalin 8 of 469, across 4 files
Said here and by no other author read
- match ideas by failure tags and structural shape
- report standing priors verbatim before interpreting
- append new entries only via the idea-killer skill
- promote any tag to a standing prior after three kills
- retire priors only on contrary external evidence
- record prior retirements without deleting history
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.