Repository navigation
docs: correct four figures and one claim both guides had outgrown - #29
Merged
Merged
Conversation
A sweep of every mechanically checkable number in CLAUDE.md and README.md against the repo. Five were wrong, all in the same direction -- written true, then overtaken by work that had no reason to revisit them. - description average 173 -> 204, and README's "kept near 160 characters" with it. #14 and #22 gave every description a negative boundary clause; that is the trade that bought fewer misfires, so the paragraph now names it rather than quoting a figure from before it. - README's "all 19 together cost a session under 800 tokens" -> about 1,000. Same cause: name + description is 4,063 characters. - allowed-tools grants containing a space, 70 -> 79, now stated as a share of the 173 total so the next drift is visible in the sentence itself. - The references/ example was Phase 2.5 in both guides, and README still said the machinery had "gone unused". Neither is true: what moved is Phase 5, into references/iteration.md, because Autonomous mode is the only mode that runs it. Phase 2.5 is named as the counter-example it actually is -- conditional, but eight lines, so a fetch costs more than it saves. Verified and left alone: 19 plugins and skills, 380 queries at 20 per plugin with a 10/10 label split and a 12/8 train/validation split, 13 eval cases at runs: 3, five verdict markers, the 320/500/300/100 thresholds, the model-tier roster, and spec-writer's 5000 words / 800 lines. No plugin changed, so nothing bumps -- neither behaviour nor catalogue copy. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
4 tasks done
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
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.
A sweep of every mechanically checkable number in
CLAUDE.mdandREADME.mdagainst the repo.Five claims were wrong, all in the same direction — written true, then overtaken by work that
had no reason to revisit them.
allowed-toolsgrants with a spacereferences/machinery (README)references/iteration.mdThe first three share one cause: #14 and #22 gave every description a negative boundary clause.
That was the trade that bought fewer misfires, so the paragraphs now name it rather than quoting
a figure from before it. The grant count is now stated as a share of the total, so the next
drift is visible inside the sentence.
The fifth is the one that was not just a number. Both guides used Phase 2.5 as the example
of what belongs in
references/, and README still said the machinery had gone unused. Neitherholds: what actually moved is Phase 5, into
references/iteration.md, because Autonomousmode is the only mode that runs it. Phase 2.5 is now named as the counter-example it really is
— conditional, but eight lines, most of them the condition itself, so a fetch would cost more
than it saves. That matters because the two paragraphs are the repo's rule for what moves;
illustrating it with a case that fails its own second test taught the wrong thing.
Verified and left alone
19 plugins and skills · 380 queries at 20 per plugin, 10/10 labels, 12/8 train/validation ·
13 eval cases at
runs: 3· five verdict markers · the 320 / 500 / 300 / 100 thresholds ·the model-tier roster (7 pins, 4 with
context: fork+background: false) ·spec-writer's 5000 words / 800 lines.No plugin changed, so nothing bumps: neither behaviour nor catalogue copy.
make test4/4,scripts/validate-fixturesandmake doctorclean.🤖 Generated with Claude Code