ai-session-audit
Audit coding-agent sessions and mine cross-harness history for recurring corrections, skill-routing gaps, and harness faults. Use…
Optional persistent file-based planning for multi-phase or long-running work that benefits from recovery across sessions or compaction. Use when requested or when persistence materially improves continuity.
$ npx -y skills add khaneliman/khanelinix --skill planning-with-files --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/planning-with-filesContext preview
The summary Claude sees to decide when to auto-load this skill.
Optional persistent file-based planning for multi-phase or long-running work that benefits from recovery across sessions or compaction. Use when requested or when persistence materially improves continuity.
name: planning-with-files description: "Optional persistent file-based planning for multi-phase or long-running work that benefits from recovery across sessions or compaction. Use when requested or when persistence materially improves continuity." metadata: version: "3.4.0"
Codex hooks require an explicit attachment before relying on planning context or Stop gating:
scripts/attach-session.sh <session-id> <plan-id>
Use `.` to intentionally attach the repository-root legacy `task_plan.md`. Unattached sessions receive no planning context or planning Stop gate.
Use persistent markdown files as working memory when a task intentionally opts into cross-session or compaction recovery. Hook behavior is provider-specific; this canonical package is the provider-neutral routing layer. Harness adapters may add hooks without changing the workflow contract.
When the current task has intentionally adopted planning state, read:
Recover missing execution evidence from the relevant task session. The bundled `scripts/session-catchup.py` searches project-wide history; use it only for an intentional historical investigation, not automatic session recovery.
from templates after choosing this workflow.
`task_plan.md`.
[templates/findings.md](templates/findings.md), [templates/progress.md](templates/progress.md)
Run packages directly with: Or install from the packages output. For example:
Audit coding-agent sessions and mine cross-harness history for recurring corrections, skill-routing gaps, and harness faults. Use…
Design and audit agent instructions, skills, plugins, subagents, prompts, hooks, and provider configuration. Use for AI-tool…
Sketch interfaces, state, and module structure before code. Use for explicit design-led implementation or as a caller-owned…
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena,…
Bevy workflows for ECS, migrations, first-party UI/input/rendering/assets/shaders, plugin selection, scenes, scheduling, hot…
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by…