npx claudepluginhub caphtech/claude-marketplace --plugin disposable-pluginWant just this skill?
Then install: npx claudepluginhub u/[userId]/[slug]
Orchestrate the full H-DGM (Hybrid Disposable Generation Method) disposable prototyping cycle. Manages spike-autopsy-distill iterations with Mode A (auto) or Mode B (manual) control. Tracks cycle history and graduation readiness. Use to start or continue a disposable prototyping session.
This skill uses the workspace's default tool permissions.
references/autopsy-schema.jsonreferences/distill-template.mdreferences/metrics-schema.jsonreferences/quality-gates.mdreferences/security-policy.mdreferences/tool-profiles.ymlDisposable Cycle — Orchestrator
Manage the full disposable prototyping lifecycle: spike → autopsy → distill → iterate or graduate.
Modes
Mode A: Automatic (default)
Full cycle runs automatically: spike → autopsy → distill → decision. User intervenes only at graduation decision or FAIL verdict.
Mode B: Manual
Each phase runs independently. User triggers each step:
/disposable-spike→/disposable-autopsy→/disposable-distill
Mode is determined by $ARGUMENTS prefix (mode:auto or mode:manual) or .disposable/config.json.
Procedure
Step 1: Initialize Session
- Check for existing
.disposable/state:- If exists, load
history.jsonand show cycle summary - If not, create
.disposable/with initial structure
- If exists, load
- Write/update
.disposable/config.json:{ "mode": "auto|manual", "maxCycles": 5, "qualityGates": {} } - Parse requirements from
$ARGUMENTS(after mode prefix)
Step 2: Cycle Loop (Mode A)
while cycle_count < maxCycles:
1. Run disposable-spike with current requirements/spec
2. Run disposable-autopsy on completed spike
3. Check verdict:
- PASS → Run disposable-distill → Check graduation → maybe exit
- CALIBRATE → Run calibration (targeted fix + re-evaluate)
- FAIL → Run disposable-distill → Prepare next spike input
4. If graduating → exit loop
5. Prepare next cycle: distill-spec becomes input for next spike
Step 3: Cycle Loop (Mode B)
Report current state and available next action:
- After initialization → suggest
/disposable-spike - After spike → suggest
/disposable-autopsy - After autopsy → suggest
/disposable-distill - After distill → suggest next
/disposable-spikeor graduation
Step 4: History Tracking
Update .disposable/history.json after each phase:
{
"cycles": [
{
"id": "cycle_1",
"startedAt": "ISO8601",
"phases": {
"spike": { "completedAt": "ISO8601", "metricsRef": "spike-complete.json" },
"autopsy": { "completedAt": "ISO8601", "verdict": "CALIBRATE" },
"distill": { "completedAt": "ISO8601" }
},
"verdict": "CALIBRATE",
"graduated": false
}
],
"currentCycle": "cycle_2",
"totalCycles": 2
}
Step 5: Graduation Decision
When autopsy verdict is PASS, evaluate graduation criteria:
- No unaddressed
mustconstraints across all cycles - Architecture decisions stable (no reversals in last 2 cycles)
- All interface contracts validated
- Open questions resolved
If criteria met:
- Present graduation summary to user
- Ask: graduate to production or iterate once more?
- If graduating:
- Compile final distill spec with all cycle learnings
- Switch to base branch:
git checkout main(or the branch active before the cycle) - Clean up spike branches:
git branch --list 'disposable/cycle_*' | sed 's/^[* ]*//' | xargs -r git branch -D - Archive
.disposable/state - Output production-ready specification
Step 6: Cleanup
On completion or user abort:
- Release
.disposable/.lock - Update
history.json - Report session summary:
- Total cycles run
- Verdict progression
- Key learnings extracted
- Final recommendation
References
- references/metrics-schema.json — Unified metrics contract
- references/autopsy-schema.json — Autopsy report contract
- references/distill-template.md — Distill specification template
- references/quality-gates.md — Quality gate definitions and calibration mode
- references/security-policy.md — Security boundary enforcement
- references/tool-profiles.yml — Language-specific tool allowlist
Configuration
.disposable/config.json options:
| Key | Default | Description |
|---|---|---|
| mode | "auto" | "auto" or "manual" |
| maxCycles | 5 | Maximum spike-autopsy-distill iterations |
| qualityGates | {} | Override quality gate thresholds (see quality-gates.md) |
| triangulation | true | Use Codex MCP for triangulated review in autopsy |
Safety
- All code generation happens on isolated
disposable/cycle_{N}branches - No network access during spike generation (see security-policy.md)
- Sensitive data masked in all artifacts (see mask-sensitive.mjs)
- Lock file prevents concurrent cycles
- Maximum cycle limit prevents infinite loops
Similar Skills
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.