Repository navigation
Cut the context a quest-start session re-sends - #808
Conversation
Quest-Claim: 998851c99fc4bb3d
Measured quest-start spend over 2026-11-14 to 11-21: 51% of requests (52% of cost) make a single read-only call, and only 6.7% make more than one tool call, while each request re-sends the whole context. Unbounded reads, re-reads, and quest's own command output are each a few percent. Add one line to the start skill asking for known reads in one response, and rewrite the quest to the week-later re-measure. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
No actionable comments were generated in the recent review. WalkthroughThe start guide now instructs agents to combine known file, range, or search requests into one response. The spend plan updates its measurement approach, verification measures, recorded choices, and re-measurement schedule for 2026-11-30. The plan title changes from medium to small priority. Merge Risk:
|
There was a problem hiding this comment.
✅ No new issues found.
Approach: sound. The PR adds one batching instruction to the start skill, aimed at the request count its measurements identify as the cost multiplier, and trims the quest to its re-measure.
Reviewed changes
assets/skills/start.md: one line telling the agent to request the reads, ranges, or searches it already knows it needs in a single response. It touches no push, merge, or post authority, and a single revert undoes it.quest/m0/start-spend.md: rewritten to the remaining re-measure, with the baseline's new batching metrics, a## Scheduledentry for 2026-11-30, and the size changed from M to S.
claude-sonnet-5-5 | 𝕏

Works on quest/m0/start-spend.md: measures where
quest-startsessions re-send context, adds one line to the start skill for the largest lever in scope, and rewrites the quest to its week-later re-measure.Summary
The quest's Plan guessed that a few large tool results, mostly shell file reads, dominate re-sent cost. Ranking every tool result in the baseline's 324 start sessions (2026-11-14 to 11-21) by tokens times the requests left before the session's next compaction did not bear that out:
quest's own gate, review, and status output is about 1%.Changes:
assets/skills/start.md: one line saying every request re-sends the whole context, so the reads a step already knows it needs go in one response.quest/m0/start-spend.md: rewritten to what remains, the re-measure, scheduled for 2026-11-30. It records the baseline with the new batching metrics (6.7% of requests make more than one tool call, 51% make a single read-only call) and the method to repeat. Resized from M to S.Public API and wire: none. The start skill's text changes.
Validation
Measurement: throwaway Python over the baseline's
token-max sessionslist and its transcripts, reusing moq-dev/quest#803's session-to-skill attribution and prices. It is kept in this worktree's.tmp/and not committed, since it reads this host's transcripts. As a check, the cost decomposition sums to the $2.5k start total the baseline reported.A/B of the line on its real surface, headless
claude -pat Opus 5.5 medium effort, running the same read-only investigation ("tracequest startfrom argument parsing to the draft PR, with file:line") under the old and new start skill text:start.md)The direction matches the rule, but the sample is small. Cost per run is flat because sessions this short don't build up context; the saving can only show in long sessions, which is what the scheduled re-measure checks.
quest skill startfrom this checkout prints the new line.quest check(26 documents ok),just check, andjust test(1,564 passed, 5 skipped) pass.Decisions
The user was away, so these are my calls, for review:
PreToolUsecheck denying unboundedcatorsed: whole-file and over-6k reads are too small a share to justify a hook that also blocks legitimate reads of small files.quest's own output: gate, review, and status output is about 1% of re-sent tool results, and the skill and context loads are what moq-dev/quest#807 already trimmed.start.mdas the quest scopes it. The rewritten quest proposes the same line foriterate.mdonly if the re-measure shows it moves the batching share.quest hookcontext reached 1 of 324 start sessions in the window. Main T3 sessions fire no SessionStart hook (this one included), and sub-agents then ran the olderquest worktree hook. It costs nothing, since sessions load the same rules throughquest context.Models
Size: M
Implementer: Claude Code, claude-opus-5-5, unknown effort (arm B)
Follow-ups
None. The remaining work is this quest's re-measure, which the rewritten quest holds.
🤖 Generated with Claude Code
(Written by Opus 5.5)
Review
Rewritten by
quest reviewafter each round.Head: dfdadb8
Base: origin/main at dbe6aab
Risk: medium,
Adds one instruction to `assets/skills/start.md`, which every `/quest-start` session loads, telling agents to batch reads they already know they need; if it misleads agents, review quality or the PR's validation could suffer for quest users, and a revert of that one line undoes it fully. It leaves push, merge, and post authority untouched, so it is not high; the plan file change is low.Classified: medium by Claude Code, claude-haiku-5-5, low effort, session
e574e667-c4ee-445d-b493-436926ec7f68Reviewer: Codex, gpt-6.1-sol, high effort
Session:
01a20218-1603-77c1-9033-377b7af9d6e2, round 1Score: 9/10,
Static review identified no actionable regressions or stale dependents; builds and tests were not run as instructed.Rounds: 1; first round 0; findings 0: fixed 0, refuted 0, open 0
Findings: none
Reviewer: Codex, gpt-6.1-sol, xhigh effort, shadow
Session:
01a20218-1606-7742-bf73-4ce993476c6b, round 1Score: 9/10,
The guidance and revised quest are internally consistent with no actionable regressions found in static review, though builds and tests were not run as instructed.Rounds: 1; first round 0; findings 0: fixed 0, refuted 0, open 0
Findings: none