Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/waitdeadai-cmax
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/cmax
What's inside
- Skill name
cmax- Description
- The default FAT umbrella. Auto-runs deepresearch + multispec decomposition + parallel /goal + verify. Opus for planning/judgment/verification; Sonnet for sub-Spec execution (escalates per router). Multispec engine selects Mode A (SDK subagents) or Mode B (Claude Code Agent Teams) automatically based on work size. Your default daily-driver.
- License
- Apache-2.0
- Instructions
- 45 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# /cmax — default daily-driver
The umbrella. You describe what you want; the pipeline produces it — **0 → production-ready, autonomously**, on a new or an existing project (it runs in the current directory).
> **One simple entry:** `cmax ask "<your goal>"` (= `/cmax`). Hardened by **default** — production-ready bar (PRC) + spec self-correction (SSC) + adversarial, decomposed, evidence-gated verify. No flags to remember. Lighten only if you want: `--mvp` (ship an MVP), `--no-ssc`, `--no-adversarial`. Granular control lives on `cmax run`.
**Ask. Achieve.** No 10-question wizards, no model picker, no decomposition-by-hand. The SOTA-2026 spec-driven + deepresearch-backed pipeline runs automatically.
## Pipeline (default behavior, no flags)
1. **Taste check** — read `taste.md` + `taste.vision` if present. If absent and the repo has signal, suggest `cmax taste init`. Don't violate taste.
2. **/deepresearch** — web-current research with source ledger. Persisted to `memory.research_sources`.
2-bis. **verify-research** (default ON, added 2026-06-09) — decomposed per-claim verification of the brief: parallel Haiku citation-support checks on the brief's own cached excerpts (no network, 60s timeouts), Sonnet escalation (one spot-fetch + one fresh search, 120s) only for findings the excerpts can't support. Contradicted findings are stripped into openQuestions; unverified ones flagged `[unverified]`; >30% escalation demand fails the brief and re-researches once. Timeouts count as unverified, never as pass.
3. **multispec decompose** — Fable 5 (while included →2026-06-22; Opus after) authors a MultiSpec: N sub-Specs (each with measurable completion conditions + verifyHints) + DAG + rollup completion conditions + per-sub-Spec writeSet.
4. **/specqa** (parallel per sub-Spec) — gate spec quality.
5. **/introspect** (parallel per sub-Spec) — confidence/assumption check. Block at confidence < 6.
6. **Mode selection** — engine picks Mode A (SDK subagents in one query()) or Mode B (Claude Code Agent Teams) based on sub-Spec count, est. duration, cross-spec coordination, write-set overlap. Override with `--mode {auto|solo|teams}`.
7. **Parallel /goal per DAG leaf** — every leaf at the current frontier runs in parallel up to the hardware + credit-aware cap. Sonnet executes sub-Specs by default; Opus on router escalations.
8. **per-sub-Spec /verify** (parallel) — blind Opus re-reads repo, re-checks each completion condition.
9. **rollup /verify** — blind Opus checks the rollupCompletionConditions across all sub-Spec outputs.
10. **Memory record** — run snapshot to `memory.runs` + state to `.claudemax/state/`.
## Variants
| Skill | Routing |
|---|---|
| `/cmax` | Default — Fable 5 plan/decompose (while included on Max, →2026-06-22; Opus after) + Sonnet/Opus exec per era + Opus verify |
| `/opusolo` | Opus exec for sub-Specs too (max effectiveness, ~3× cost) |
> The `/workflow` + `/opussonnet` aliases were removed 2026-05-28; the `opussonnet`/`opusolo` exec-tier variants remain via `cmax run --variant`. Fable 5 defaults auto-demote to Opus on 2026-06-23 when Fable bills usage credits (`CMAX_FABLE_ACCESS=included|credits` flips the configurations); `cmax loop run --fable` / `--tier fable` reach Fable explicitly in both modes — see `docs/MODEL_ROUTING.md`.
## Hard rules
- Never declare success on the strength of the executor's own claim. The blind /verify is the source of truth.
- Verify and spec always run on Opus, never demoted regardless of credit % or `--cheap`.
- If /verify returns partial or failed, iterate /goal against the failing conditions; re-verify. If two iterations don't move it, the SPEC is probably wrong — re-spec, don't re-grind.
- Cost-guard kicks in at 70% of monthly Agent SDK credit (demote non-essential Opus → Sonnet); at 90% aggressive demote; at 95% `--force` required.
## When NOT to invoke /cmax
- Trivial one-line changes — just edit.
- A single SPEC that fits in one /goal loop — invoke `/goal` directly on the existing SPEC.md.
- Pure research with no implementation — invoke `/deepresearch` directly.From waitdeadai/claudemax, Apache-2.0.
More from waitdeadai/claudemax
- 0.497score
hive
waitdeadai
Same problem given to N agents in parallel; merge proposals.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
orchestrate
waitdeadai
Multi-goal harness — runs N `/cmax` pipelines in parallel for DIFFERENT goals at the same time.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
investigate
waitdeadai
Multi-source root-cause analysis for a specific bug or failure.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
mega
waitdeadai
Session-limit-aware mega-build orchestrator.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
council
waitdeadai
3-Opus adversarial debate (proposer / critic / judge) for architectural decisions.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
deepresearch
waitdeadai
Iterative web-current research with source ledger.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
align
waitdeadai
One-shot semantic decision recorder.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
goal
waitdeadai
Autonomous Opus loop that pursues a SPEC across multiple turns until every completion condition is satisfied or a real blocker surfaces.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
harness-audit
waitdeadai
Periodic review of claudemax's own scaffolding against the current Opus capability.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
introspect
waitdeadai
Confidence/assumption hard-gate before /goal handoff.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
memory
waitdeadai
Durable cross-session memory for claudemax.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
opusolo
waitdeadai
Max-effectiveness umbrella.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- Jun 9, 2026 (4 months ago)
- Last release
- May 20, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/waitdeadai/claudemax
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from waitdeadai
- 0.497score
hive
waitdeadai
Same problem given to N agents in parallel; merge proposals.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
mega
waitdeadai
Session-limit-aware mega-build orchestrator.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
council
waitdeadai
3-Opus adversarial debate (proposer / critic / judge) for architectural decisions.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
deepresearch
waitdeadai
Iterative web-current research with source ledger.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
investigate
waitdeadai
Multi-source root-cause analysis for a specific bug or failure.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
orchestrate
waitdeadai
Multi-goal harness — runs N `/cmax` pipelines in parallel for DIFFERENT goals at the same time.
SkillCFreshness: C★ 1Claude Code +9
Cite this page
cmax skill. Agent Mart. https://agentmart.dev/skills/waitdeadai-cmax (last updated 2026-10-24)