Replace shared CSV files (AGENT_TASK_LOG.csv, WEEKLY_AGENT_TASK_LOG.csv)
with per-entry files in docs/agents/task-logs/{daily,weekly}/. Each log
entry is now a separate file named YYYY-MM-DD_HH-MM-SS_<agent>_<status>.md,
eliminating git merge conflicts and race conditions when multiple agents
run concurrently.
Updated files:
- daily-scheduler.md: rewritten for directory-based log format
- weekly-scheduler.md: rewritten for directory-based log format
- META_PROMPTS.md: updated pre-flight scan and claiming instructions
- AGENTS.md: updated scheduler reference from CSV to directory-based
Migrated all existing CSV entries to individual files in the new
directory structure.
https://claude.ai/code/session_01P62EWUXwupgxPhpnRejUuz
- Move `CONTEXT.md`, `TODO.md`, `DECISIONS.md`, `TEST_LOG.md` to `context/`, `todo/`, `decisions/`, `test_logs/` directories with timestamps.
- Update `AGENTS.md` and `CLAUDE.md` to define the new workflow: agents must read the latest timestamped file and create a new one when updating.
- Update `daily-scheduler.md` and `weekly-scheduler.md` to initialize tasks using the new file structure.
- Update all daily agent prompts to reference the new directory structure.
- This change prevents merge conflicts on persistent state files by treating them as an append-only log of snapshots.
Co-authored-by: PR0M3TH3AN <[email protected]>
When multiple agents (Claude Code, Codex, Jules) run schedulers concurrently,
they can pick up the same task because neither has committed yet. This adds a
"Draft PR Lock" protocol: agents must check for and create a draft PR before
starting work, acting as a distributed lock visible to all platforms.
Changes:
- AGENTS.md §12: new "Task Claiming Protocol" subsection with check/claim/race
handling steps
- daily-scheduler.md: new Step 1.5 with concrete gh CLI commands
- weekly-scheduler.md: same Step 1.5 addition
https://claude.ai/code/session_01Vnih5ZARbEmnh3EGTDQAXX
Introduces a structured meta-workflow for AI agents that ensures
safe incremental changes, persistent state across context resets,
and a clear decision trail for multi-agent coordination.
Key additions:
- Work scoping (goal, success criteria, non-goals)
- External notes files (CONTEXT.md, TODO.md, DECISIONS.md, TEST_LOG.md)
- Locate → Implement → Verify → Update notes work loop
- Context recovery procedure for new agent sessions
- Quality bar principles
- Cross-references from CLAUDE.md to the new section
https://claude.ai/code/session_0159eSJrqKvKpgDiwYZ2iGxK
Updates AGENTS.md and README.md to reflect the configurable hybrid playback strategy (URL vs. WebTorrent) instead of asserting a strict "URL-First" rule, which contradicted the default configuration.
- Updated "Mission" in AGENTS.md to "Hybrid Playback Strategy".
- Clarified that `DEFAULT_PLAYBACK_SOURCE` controls priority.
- Updated README.md "How playback works" section.
- Adjusted QA checklists to focus on "configured priority" rather than "URL-first".
Co-authored-by: PR0M3TH3AN <[email protected]>
Section 14 in AGENTS.md covers the full test harness API, mock relay
HTTP endpoints, Playwright fixture usage, and data-testid selector
reference. CLAUDE.md testing section updated with quick-start example.
https://claude.ai/code/session_01XnrszNmdqrAGd8g8qhAn4G
Three CI-enforced lint scripts to prevent common codebase growth problems:
- lint:file-size — enforces 1000-line max for new JS files, grandfathers
existing oversized files and prevents them from growing further
- lint:innerhtml — tracks innerHTML usage per-file with a baseline count,
blocks new innerHTML additions (guides agents toward safe DOM APIs)
- Relay constants consolidated from duplicate definitions in client.js and
ConnectionManager.js into shared js/nostr/relayConstants.js
- AGENTS.md Section 13: documents all three rules with examples
- docs/scheduled-agent-prompts.md: copy-paste prompts for recurring
file decomposition, innerHTML migration, and constant dedup tasks
https://claude.ai/code/session_01LzErpH9FNw4hAPsjoYb1v9
- AGENTS.md Section 12: subsystem boundary table, PR discipline rules,
in-flight work reservation section, and signaling conventions for
parallel AI agent workflows (Claude Code, Codex, Jules)
- CLAUDE.md: document the unstable→beta→main promotion pipeline,
add multi-agent workflow section with coordination rules for both
agents and human maintainers, fix Node.js version reference (20→22)
https://claude.ai/code/session_01LzErpH9FNw4hAPsjoYb1v9
Updates documentation to match current codebase implementation:
- Deprecates `nostrClient.fetchVideos` in README.md, pointing to `subscribeVideos`.
- Clarifies `playVideoWithFallback` implementation location in `docs/playback-fallback.md` and `AGENTS.md` (moved to `js/app/playbackCoordinator.js`).
- Corrects `WATCH_HISTORY` d-tag description in `docs/nostr-event-schemas.md` to match actual code behavior (`<YYYY-MM>`).
Co-authored-by: PR0M3TH3AN <[email protected]>
Updates AGENTS.md to explicitly instruct AI agents to review
KNOWN_ISSUES.md before starting development or debugging. This
ensures awareness of pre-existing test failures and environmental
quirks, preventing unnecessary investigation.
Update AGENTS.md to explicitly require support for both legacy NIP-04 and newer NIP-44 Direct Messages, as many users still rely on the legacy standard.
Adds a new section to `AGENTS.md` documenting the importance of using
the `d` tag (network identifier) over logical IDs (like `videoRootId`)
when creating pointers for parameterized replaceable events (NIP-33).
This captures the lessons learned from recent watch history bugs where
mismatched identifiers caused hydration failures.
Claude