bibcheck: split modes into sibling files and extract splitter script#13
Open
nsmiller2501 wants to merge 2 commits into
Open
bibcheck: split modes into sibling files and extract splitter script#13nsmiller2501 wants to merge 2 commits into
nsmiller2501 wants to merge 2 commits into
Conversation
Move Step 3a (per-citation) and Step 3b (per-field) prompt templates and consolidator passes into mode_per_citation.md and mode_per_field.md. Only one mode fires per invocation, so the split saves loaded tokens on every run. SKILL.md drops 144 -> 97 lines (under the 100-line rubric cap).
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Two small follow-up changes to
/bibcheck. (1) Splits the two operating modes (per-citation, per-field) into sibling files so SKILL.md only carries shared context. (2) Extracts the inline.bibsplitter into a standalone script underscripts/split_bib.py.Both changes are intended to reduce per-invocation token cost without altering audit behavior.
What changed
mode_per_citation.md: holds the Step 3a prompt template + consolidator pass for the default--by-citationmode.mode_per_field.md: holds the Step 3b prompt template + consolidator pass for--by-field.SKILL.mdshrinks from 144 → 97 lines, pointing into whichever mode file is selected. Since only one mode fires per invocation, the unused mode no longer occupies the loaded context.scripts/split_bib.py: the previously inline.bibsplitting logic, extracted to a reusable script. SKILL.md now invokes it via~/.claude/skills/bibcheck/scripts/split_bib.pyand references it inallowed-tools.Why
.bib-chunking logic out of the LLM context entirely and makes it independently testable / re-runnable.Testing
mode_per_citation.mdandmode_per_field.mdcarry the exact prompt templates and consolidator instructions that previously lived in SKILL.md.SKILL.mdreferences the new sibling files and the extracted script path.split_bib.pyagainst a sample.bibto confirm chunking output matches the prior inline behavior.