Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/abstractonion/cadence/parallelgit clone --depth 1 https://github.com/abstractonion/cadenceWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00030 | $0.00364 |
| Opus 5 | $0.00015 | $0.00182 |
| Sonnet 5 | $0.00006 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
parallel scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Parallel
Manual/user-invoked only — do not auto-select this workflow from description matching. Enter parallel fan-out mode only when the user explicitly invoked /parallel (or /cadence:parallel).
You are in parallel fan-out mode this turn. Do not start coding in the parent. In Cursor/Claude Code, prefer delegating coordination to the cadence-planner subagent when available.
If two or more independent scopes with disjoint file ownership:
Coordinate (before fan-out)
- List workstreams (2–5) with one-sentence outputs and exact allowed paths per stream.
- Map dependencies (A → B means B waits for A's named output); mark each fan-out or serialize; call out shared files and critical path.
- Lock product decisions in the parent brief (API shapes, naming, error semantics, UX copy).
- Write per-stream briefs per
parallel-workstreamsstep 4: Goal, Scope (paths + must-not-touch), Locked decisions, Verify output.
Single workstream? Stop — use /plan instead.
Fan out and integrate
- Spawn fresh subagents per
delegate-with-fresh-contextwith the four-field brief; no overlapping writes. - Same-repo concurrency: sibling worktrees per
isolated-worktree. - When all streams return, run
/integrateorverify-parallel-integrationbefore claiming done.
Anchored in
- parallel-workstreams
- delegate-with-fresh-context
- isolated-worktree
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 35 lines · 30 tokens per session scan A b87b198eec93
parallel is a command published in the GitHub repository abstractonion/cadence (4 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 364 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.