Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →alinaqi/context-shunt
Offload large / multi-file reads to a cheap worker model so raw files never enter Claude's context (token savings)
Passed 21 of 22 test cases with the skill, and 6 of 22 without it.
and 12 more in the full report
15 fixed6 passed either way1 still failing0 broke1 errored
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
What environment variable configures whether the PreToolUse hook operates in suggest, block, or off mode, and what action mode does it default to?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies SHUNT_MODE as the environment variable. | Missed | Passed |
| Identifies suggest as the default action mode. | Passed | Passed |
The instructions your model reads when the skill loads.
Reading big files into context is the most expensive thing an agent does for the
least reasoning value. The shunt hands those reads to a cheap worker model
(bulk-read) that answers a question about the files and returns a compact
summary. The raw bytes never enter this session's context.
This is orthogonal to whole-turn routing (srooter / route-task): those pick the
model for the turn; the shunt trims what a tool call pulls into context when
the turn is legitimately here.
bulk-read "<question>" file....get_code_snippet(qualified_name): free and exact.A shunt answer is for understanding, not for producing a diff.
bulk-read "how does token refresh work?" src/auth/session.ts src/auth/refresh.ts
bulk-read "which config keys are read at startup?" $(git ls-files 'config/*.yaml')
bulk-read prints structured bullets citing path:line, or
NOT FOUND IN PROVIDED FILES. A token-savings report goes to stderr.
Env vars or ~/.claude/shunt.conf (see templates/shunt.conf):
SHUNT — on/off master switch for the PreToolUse hook.SHUNT_MIN_LINES — large-read threshold (default 350).SHUNT_MODE — suggest (default) / block / off for the hook's large-read action.SHUNT_GRAPH_NUDGE — on/off once-per-session graph nudge.SHUNT_MODEL — worker command (default deepseek --flash; also gemini-api --flash-lite, qwen3, glm).test cases passed, vs 6 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.