ReddRadar
Agent skill
session-resume
Session resume protocol and session repairs handling. Loaded when spellbook_session_init returns resume_available: true, or when session_init returns a repairs array. Triggers: 'resume', 'continue', 'where were we', session resume, session repairs.
Install this agent skill to your Project
npx add-skill https://github.com/axiomantic/spellbook/tree/main/skills/session-resume
SKILL.md
Invariant Principles
- Boot Prompt Executes Immediately - The resume boot prompt runs before any other user interaction; it is not optional or deferrable.
- Continuation Intent Governs Action - The user's first message determines whether to resume, start fresh, or default to resume; never assume.
- Corrupted State Is Announced, Not Silently Skipped - If todos or workflow state is malformed, inform the user explicitly rather than proceeding with partial data.
Session Resume Protocol
When spellbook_session_init returns resume_available: true, follow this protocol exactly.
Resume Fields
| Field | Type | Description |
|---|---|---|
resume_available |
bool | Recent session (<24h) exists |
resume_session_id |
string | Session soul ID |
resume_age_hours |
float | Hours since bound |
resume_bound_at |
string | ISO bind timestamp |
resume_active_skill |
string | Active skill (e.g., "develop") |
resume_skill_phase |
string | Skill phase (e.g., "DESIGN") |
resume_pending_todos |
int | Incomplete todo count |
resume_todos_corrupted |
bool | Todo JSON malformed |
resume_workflow_pattern |
string | Workflow (e.g., "TDD") |
resume_boot_prompt |
string | Section 0 boot prompt |
Resume Execution
- Execute
resume_boot_promptIMMEDIATELY (Section 0 actions) - Section 0 includes: skill invocation with
--resume <phase>if active,Read()for planning docs,TodoWrite()for todo state, behavioral constraints from prior session - After Section 0, announce restoration in greeting
If resume_todos_corrupted: true: announce to user that todo state was malformed and requires manual restoration.
Continuation Detection
| Pattern | Intent | Action |
|---|---|---|
| "continue", "resume", "where were we" | continue | Execute boot prompt |
| "start fresh", "new session", "clean slate" | fresh_start | Skip resume, return resume_available: false |
| "ok", "next", neutral message | neutral | Execute boot prompt (if session exists) |
Session Repairs
When spellbook_session_init returns a repairs array, display each repair according to its severity:
| Severity | Action |
|---|---|
error |
Display prominently. These may affect functionality. |
warning |
Display as informational. Suggest the fix command. |
Example Greeting with Repairs
Welcome to spellbook-enhanced Claude.
Repairs needed:
- TTS is enabled but kokoro is not installed. Fix:
uv pip install 'spellbook[tts]'
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
axiomantic/spellbook
spellbook-auditing
Meta-audit skill for spellbook development. Spawns parallel subagents to factcheck docs, optimize instructions, find token savings, and identify MCP candidates. Produces actionable report.
axiomantic/spellbook
documentation-updates
Use after modifying library skills, library commands, or agents to ensure CHANGELOG, README, and docs are updated
axiomantic/spellbook
project-encyclopedia
[DEPRECATED] Use project-level AGENTS.md files instead. Previously used for first-session codebase onboarding and persistent glossary creation.
axiomantic/spellbook
reviewing-impl-plans
Use when reviewing implementation plans before execution. Triggers: 'is this plan solid', 'review the plan', 'check before I start building', 'anything missing from this plan', 'will this plan work', 'audit the implementation plan'. NOT for: reviewing design documents (use reviewing-design-docs) or creating plans (use writing-plans).
axiomantic/spellbook
brainstorming
Use when exploring design approaches, generating ideas, or making architectural decisions. Triggers: 'explore options', 'what are the tradeoffs', 'how should I approach', 'let's think through', 'sketch out an approach', 'I need ideas for', 'how would you structure', 'what are my options'. Also invoked by develop when design decisions are needed.
axiomantic/spellbook
debugging
Use when debugging bugs, test failures, or unexpected behavior. Triggers: 'why isn't this working', 'this doesn't work', 'X is broken', 'something's wrong', 'getting an error', 'exception in', 'stopped working', 'regression', 'crash', 'hang', 'flaky test', 'intermittent failure', or when user pastes a stack trace/error output. NOT for: test quality issues (use fixing-tests), adding new behavior (use develop).
Didn't find tool you were looking for?