8 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
naps62-yolo	74632e5929	test(evals): cover cross-forge PR skill rollouts (#25)	2026-09-06 14:01:36 +01:00
naps62-yolo	d1a198ab8b	fix(pr-daemon): rate-limit hints; price the gpt-5.6 models (#21)	2026-08-28 19:40:50 +01:00
naps62-yolo	ae927736a0	feat(hooks): secret-guard blocks live secret values in tool args (#17)	2026-08-21 21:57:58 +01:00
naps62-yolo	51fd18b23e	feat(pr): hidden agent-meta marker on posted bodies (#16)	2026-08-21 16:36:40 +01:00
naps62-yolo	2f092f9ee0	feat(ci): lint skills, refs and installer drift (#15)	2026-08-20 14:23:19 +01:00
naps62-yolo	cf5518227e	feat(intercomms): let sessions find and talk to each other (#14)	2026-08-20 14:22:34 +01:00
naps62-yoloandClaude Opus 5	c8de8bcb5a	feat(nightshift): ship as a pull request, not straight to main ... A night of autonomous work needs a review gate, especially on a live repo. Output is now one branch and one PR rather than commits on the default branch. Separates committing from pushing, which had been conflated. Local commits are what protect against an agent dying mid-task, and they cost no CI, so they stay at every milestone. Pushing is what triggers CI, so it becomes a deliberate act: at the end, when parking, or on request. A night of milestone pushes is a night of CI runs on work that was half-finished at the time, which trains the user to ignore the build. Subagents are told to commit locally and explicitly not to push. Covers both forges: gh for GitHub, the API for Gitea (no tea CLI on most setups), and reporting a compare URL rather than faking success if auth fails. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_019SSXDKsik8yYrezStVaDXt	2026-07-25 13:15:57 +00:00
naps62-yoloandClaude Opus 5	3163bd26f0	feat(nightshift): long autonomous build skill with limit backoff ... Takes an issue, ticket or plain description and works it for hours as an architect: freeze the interface contract first, then delegate implementation to subagents against frozen signatures, review, commit every milestone. Checks the rolling 5-hour window before each dispatch and parks rather than letting agents die mid-task. The usage script sums every Claude Code session on the machine, and is explicit that it is a floor — it cannot see other machines, claude.ai, or direct API use — so the reactive backstop of an agent dying on a limit error is documented as the stronger signal. Encodes what worked in practice: disjoint file ownership per agent, asking agents to report disagreement (their pushback was the highest-value output), sabotage-testing every safety net, and asking what a passing check is structurally unable to see. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_019SSXDKsik8yYrezStVaDXt	2026-07-25 13:08:41 +00:00