Add cicada-husk — token-lean operating discipline (read-only, ~0 tokens/turn) - #331
Open
blazephoenixxyz-crypto wants to merge 1 commit into
Open
Add cicada-husk — token-lean operating discipline (read-only, ~0 tokens/turn)#331blazephoenixxyz-crypto wants to merge 1 commit into
blazephoenixxyz-crypto wants to merge 1 commit into
Conversation
A token-lean operating discipline for Claude Code: read code by symbol instead of by whole file, cite prior findings by name, dose effort per task, and budget every sub-agent by risk. Fully read-only — two commands, one script, one ~25-token session banner, ~0 tokens per turn.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds cicada-husk under Development Engineering, in alphabetical position.
What it does. Teaches the agent to spend far fewer tokens without cutting quality or safety: read code by symbol instead of by whole file, cite prior findings by name rather than re-deriving them, dose effort to the task, never poll in a loop, budget every sub-agent by risk, and route each task to the lightest tool that is still fully safe.
Why it may interest this list. The plugin applies its own doctrine to itself. A plugin is billed only where bytes enter the model's context, so the knowledge ships as documentation (free at runtime) and the runtime surface is deliberately tiny: two commands, one portable shell script, one ~25-token session banner, ~0 tokens per turn — no per-turn spikes by construction.
Safety. Fully read-only. No daemon, no background process, nothing that can touch your files, memory or state.
docs/doctrine.mdHappy to move it to a different category if you would rather see it under Thinking & Knowledge Management.