2026-06-25 - 2026-07-25

Overview

0 Active Pull Requests
25 Active Issues
Excluding merges, 2 authors have pushed 52 commits to main and 52 commits to all branches. On main, 51 files have changed and there have been 4387 additions and 5833 deletions.

22 Issues closed from 2 users

Closed #36 fieldtest: bundle friction/spec-gap findings into collective issues instead of one-per-finding 2026-07-24 20:34:15 +02:00

Closed #27 Remove the postmortem skill 2026-07-21 10:09:50 +02:00

Closed #32 implement-loop resume ignores plan edits (cached extractor) and trips the discard guard after a subset commit 2026-07-21 10:09:50 +02:00

Closed #25 implement-loop: anchor the quality reviewer to the loop's repo root (worktree sessions review the wrong tree) 2026-07-17 16:01:20 +02:00

Closed #28 Aggregate Workflow run logs in postmortem.py — workflow sessions read as zero subagent spend 2026-07-17 16:01:20 +02:00

Closed #29 Cut fixed per-iteration dispatch overhead in implement-loop; add the missing standard-mode suite gate 2026-07-17 16:01:20 +02:00

Closed #30 Tier the quality review by independently-measured diff size 2026-07-17 16:01:20 +02:00

Closed #31 Tier the standing reading for schema-bound workflow stages 2026-07-17 16:01:20 +02:00

Closed #26 Verify agent tracker actions run under the dedicated claude account 2026-07-12 13:25:44 +02:00

Closed #23 implement-loop: a task's git checkout -- <file> recovery silently discards earlier tasks' uncommitted edits to that file 2026-07-09 11:27:52 +02:00

Closed #24 Named-workflow args arrive as a string: carriers silently undefined, misreported as substantive verdicts 2026-07-09 11:27:52 +02:00

Closed #22 implement-loop: guard the plan-extract against silent truncation on big plans 2026-07-06 14:14:50 +02:00

Closed #21 boss: after the primary task, continue to autonomously-doable open follow-ups instead of stopping at a manufactured done-state 2026-07-02 13:35:35 +02:00

Closed #19 Reform brainstorm: replace the serial interview with a grounded synthetic-user swarm 2026-06-30 22:59:42 +02:00

Closed #16 Define the /boss session anchor as the captured start HEAD, not the live main ref 2026-06-30 14:17:51 +02:00

Closed #17 Add install.sh --force to repoint symlinks and document the worktree caveat 2026-06-30 14:17:51 +02:00

Closed #18 Document the worktree slug caveat for the postmortem default log dir 2026-06-30 14:17:51 +02:00

Closed #15 Add a repo CLAUDE.md forbidding worktree development of the plugin 2026-06-30 13:35:46 +02:00

Closed #12 implement-loop: iteration DONE has no positive-evidence precondition (the #11 no-op-reads-as-success pattern in the main path) 2026-06-29 11:08:57 +02:00

Closed #13 grounding-check: a vacuous PASS (zero assumptions extracted) auto-signs the spec under /boss 2026-06-29 11:08:57 +02:00

Closed #14 Convert prose-only no-op guards to structural floors (fieldtest examples, audit drift-review) 2026-06-29 11:08:57 +02:00

Closed #11 compiler-driven-edit returns DONE on a no-op edit (verdict vacuously true on a clean tree) 2026-06-27 13:31:53 +02:00

25 Issues created by 1 user

Opened #11 compiler-driven-edit returns DONE on a no-op edit (verdict vacuously true on a clean tree) 2026-06-26 23:29:44 +02:00

Opened #12 implement-loop: iteration DONE has no positive-evidence precondition (the #11 no-op-reads-as-success pattern in the main path) 2026-06-27 13:21:58 +02:00

Opened #13 grounding-check: a vacuous PASS (zero assumptions extracted) auto-signs the spec under /boss 2026-06-27 13:21:58 +02:00

Opened #14 Convert prose-only no-op guards to structural floors (fieldtest examples, audit drift-review) 2026-06-27 13:21:59 +02:00

Opened #15 Add a repo CLAUDE.md forbidding worktree development of the plugin 2026-06-30 13:34:48 +02:00

Opened #16 Define the /boss session anchor as the captured start HEAD, not the live main ref 2026-06-30 14:14:55 +02:00

Opened #17 Add install.sh --force to repoint symlinks and document the worktree caveat 2026-06-30 14:14:55 +02:00

Opened #18 Document the worktree slug caveat for the postmortem default log dir 2026-06-30 14:14:55 +02:00

Opened #19 Reform brainstorm: replace the serial interview with a grounded synthetic-user swarm 2026-06-30 22:58:56 +02:00

Opened #21 boss: after the primary task, continue to autonomously-doable open follow-ups instead of stopping at a manufactured done-state 2026-07-01 17:20:42 +02:00

Opened #22 implement-loop: guard the plan-extract against silent truncation on big plans 2026-07-06 13:42:55 +02:00

Opened #23 implement-loop: a task's git checkout -- <file> recovery silently discards earlier tasks' uncommitted edits to that file 2026-07-07 16:30:06 +02:00

Opened #24 Named-workflow args arrive as a string: carriers silently undefined, misreported as substantive verdicts 2026-07-09 10:41:40 +02:00

Opened #25 implement-loop: anchor the quality reviewer to the loop's repo root (worktree sessions review the wrong tree) 2026-07-10 20:57:36 +02:00

Opened #26 Verify agent tracker actions run under the dedicated claude account 2026-07-12 13:25:44 +02:00

Opened #27 Remove the postmortem skill 2026-07-14 12:48:57 +02:00

Opened #28 Aggregate Workflow run logs in postmortem.py — workflow sessions read as zero subagent spend 2026-07-17 15:20:05 +02:00

Opened #29 Cut fixed per-iteration dispatch overhead in implement-loop; add the missing standard-mode suite gate 2026-07-17 15:20:05 +02:00

Opened #30 Tier the quality review by independently-measured diff size 2026-07-17 15:20:05 +02:00

Opened #31 Tier the standing reading for schema-bound workflow stages 2026-07-17 15:20:06 +02:00

Opened #32 implement-loop resume ignores plan edits (cached extractor) and trips the discard guard after a subset commit 2026-07-21 07:36:16 +02:00

Opened #33 fieldtester: committed fixture labs must not reference the engine via the run worktree's absolute path 2026-07-21 14:16:41 +02:00

Opened #34 Reconcile the task_text_path carrier contract with implement-loop's inline task-text handoff 2026-07-21 19:25:17 +02:00

Opened #35 Experiment: full pipeline with implement-skills disabled — quality vs token tracking 2026-07-24 15:42:55 +02:00

Opened #36 fieldtest: bundle friction/spec-gap findings into collective issues instead of one-per-finding 2026-07-24 17:26:26 +02:00