Use when you need agent memory, file locks, or verify-before-conclude across runs and concurrent agents on a coding task — before/after big changes, edits, design, or handoffs in a shared or dirty local repo. Self-awareness — recall shared memory + work-handoff refinements (open/ongoing/done) before acting (recall is salience-decayed), record reusable lessons after. Self-harness — verify before you conclude (run your test-plan and record it; never claim success on an unverified intent), mine recurring failures, and propose refinements to code or the harness when asked or when you sense one is needed. Files-awareness — you MUST take a pre-flight file lock BEFORE creating, editing, or deleting any file, then release; check status and timestamps first. Triggers on agent memory, refinements, file locks, shared-workspace edits, dirty working tree, handoffs, repeated failures, unverified conclusions, or harness/code refinement.
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryEngineeringStars0
About this skill
Use when you need agent memory, file locks, or verify-before-conclude across runs and concurrent agents on a coding task — before/after big changes, edits, design, or handoffs in a shared or dirty local repo. Self-awareness — recall shared memory + work-handoff refinements (open/ongoing/done) before acting (recall is salience-decayed), record reusable lessons after. Self-harness — verify before you conclude (run your test-plan and record it; never claim success on an unverified intent), mine recurring failures, and propose refinements to code or the harness when asked or when you sense one is needed. Files-awareness — you MUST take a pre-flight file lock BEFORE creating, editing, or deleting any file, then release; check status and timestamps first. Triggers on agent memory, refinements, file locks, shared-workspace edits, dirty working tree, handoffs, repeated failures, unverified conclusions, or harness/code refinement.
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Use when you need agent memory, file locks, or verify-before-conclude across runs and concurrent agents on a coding task — before/after big changes, edits, design, or handoffs in a shared or dirty local repo. Self-awareness — recall shared memory + work-handoff refinements (open/ongoing/done) before acting (recall is salience-decayed), record reusable lessons after. Self-harness — verify before you conclude (run your test-plan and record it; never claim success on an unverified intent), mine recurring failures, and propose refinements to code or the harness when asked or when you sense one is needed. Files-awareness — you MUST take a pre-flight file lock BEFORE creating, editing, or deleting any file, then release; check status and timestamps first. Triggers on agent memory, refinements, file locks, shared-workspace edits, dirty working tree, handoffs, repeated failures, unverified conclusions, or harness/code refinement.
About this listing
Category
Engineering
Reported license
MIT
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLI