axiomantic/session-mode-init
skills/session-mode-init/SKILL.md
Loaded at session start when spellbook_session_init returns mode data, or when mode.type is 'unset'. Triggers: session init mode handling, '/mode', mode selection, 'fun mode', 'tarot mode'.
$ install --global
skillsauthnpx skillsauth add axiomantic/spellbook session-mode-initInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 3, 2026, 3:17 PM138.1s1 file scanned
SKILL.md
- name:
- session-mode-init
- description:
- Loaded at session start when spellbook_session_init returns mode data, or when mode.type is 'unset'. Triggers: session init mode handling, '/mode', mode selection, 'fun mode', 'tarot mode'.
<analysis>
Procedure for reading mode type from session init and dispatching to the correct mode skill or prompting the user for selection.
</analysis>
<reflection>
Did I dispatch to the correct mode skill based on the session init response, and did I persist the user's choice if mode was unset?
</reflection>
Session Mode Init
Invariant Principles
- Ask Once, Persist - The mode selection question is asked only when mode is unset; the choice is persisted via
spellbook_config_set. - Mode Drives Skill, Not Behavior - Mode selection loads the corresponding skill; mode never alters code output or technical decisions.
- Graceful Degradation - If MCP is unavailable, remember the preference in-session without blocking initialization.
Reference procedure for selecting and dispatching session modes during session initialization.
Mode Dispatch Table
| Response from spellbook_session_init | Action |
| --------------------------------------------- | ---------------------------------------------------------------------------------------------------- |
| mode.type: "unset" | Ask question below, then call spellbook_config_set(key="session_mode", value="fun"/"tarot"/"none") |
| mode.type: "fun" + persona/context/undertow | Load fun-mode skill, announce persona+context+undertow in greeting |
| mode.type: "tarot" | Load tarot-mode skill, announce roundtable in greeting |
| mode.type: "none" | Proceed normally with standard greeting |
| MCP unavailable | Ask mode question manually, remember preference for session |
Mode Selection Question
Ask once when mode is unset:
Research suggests creative modes improve LLM output via "seed-conditioning" (Nagarajan et al., ICML 2025). I can adopt:
- Fun mode: Random personas each session (dialogue only, never in code)
- Tarot mode: Ten archetypes collaborate via visible roundtable (Magician, Priestess, Hermit, Fool, Chariot, Justice, Lovers, Hierophant, Emperor, Queen)
- Off: Standard professional mode
Which do you prefer? (Use
/mode fun,/mode tarot, or/mode offanytime to switch)
Procedure
- Read
mode.typefromspellbook_session_initresponse. - Match against dispatch table above.
- If
"unset": present the selection question, wait for user answer, then callspellbook_config_set(key="session_mode", value=<chosen>). - If
"fun"or"tarot": load the corresponding skill (fun-modeortarot-mode) and incorporate its output into the session greeting. - If
"none"or MCP unavailable: no further action needed for mode.
Related Skills
axiomantic/writing-skills
testing
VerifiedTrustedCommunity
Use when creating new skills, editing existing skills, or verifying skills work before deployment. Triggers: 'write a skill', 'new skill', 'create a skill', 'skill doesn't work', 'skill isn't firing', 'edit skill', 'skill quality'. NOT for: general prompt improvement (use instruction-engineering) or command creation (use writing-commands).
5SKILL.mdUpdated Apr 3, 2026
axiomantic/writing-plans
development
VerifiedTrustedCommunity
Use when you have a spec, design doc, or requirements and need a detailed implementation plan before coding. Triggers: 'write a plan', 'create implementation plan', 'plan this out', 'break this down into steps', 'convert design to tasks', 'implementation order'. Also invoked by develop during planning. NOT for: reviewing existing plans (use reviewing-impl-plans).
5SKILL.mdUpdated Apr 3, 2026
axiomantic/writing-commands
testing
VerifiedTrustedCommunity
Use when creating new commands, editing existing commands, or reviewing command quality. Triggers: 'write command', 'new command', 'create a command', 'review command', 'fix command', 'command doesn't work', 'add a slash command'. NOT for: skill creation (use writing-skills).
5SKILL.mdUpdated Apr 3, 2026
axiomantic/verifying-hunches
development
VerifiedTrustedCommunity
Use when about to claim discovery during debugging. Triggers: "I found", "this is the issue", "I think I see", "looks like the problem", "that's why", "the bug is", "root cause", "culprit", "smoking gun", "aha", "got it", "here's what's happening", "the reason is", "causing the", "explains why", "mystery solved", "figured it out", "the fix is", "should fix", "this will fix". Also invoked by debugging, scientific-debugging, systematic-debugging before any root cause claim.
5SKILL.mdUpdated Apr 3, 2026