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/kesteva/soloflow/compoundgit clone --depth 1 https://github.com/kesteva/soloflowWhat 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 | $0.00064 | $0.08869 |
| Opus 5 | $0.00032 | $0.04435 |
| Sonnet 5 | $0.00013 | $0.01774 |
| Haiku 4.5 | $0.00006 | $0.00887 |
Grade A, and why
compound 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.
How it starts
The opening of the file, as written. The whole thing — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/soloflow:compound
Phase 6 of the SoloFlow pipeline. Reads done reports, stuck reports, human review notes, and out-of-scope findings queues, then produces a three-bucket proposal for the user to review one bucket at a time. The main agent (you) applies approved items directly for clean-ups and CLAUDE.md edits, and spawns the task-refiner for backlog tasks.
Batching. When two or more sprints are pending, --all (or a multi-select picker) batches them into ONE compounder invocation → ONE merged proposal (SPRINT-{MIN}-{MAX}-proposal.md) → ONE review flow → ONE apply pass. Each sprint's findings file still archives individually. Single-sprint runs are unchanged (no span, no batching logic engages).
Target: $ARGUMENTS (optional — sprint selector). Accepted values:
SPRINT-NNN— compound that specific sprint (single-sprint path)--all— batch every pending sprint into one merged proposal--oldest— silently pick the oldest pending sprint (single-sprint path)- empty — single pending sprint auto-selected; multi-select picker when two or more exist (user can pick a subset, all, or type free-text IDs for unusual subsets)
Model resolution (applies to every Agent spawn below)
Before invoking the Agent tool, resolve models.<name> per the three-tier
recipe in docs/CUSTOMIZATION.md#config-resolution
and pass the resolved value as the Agent tool's model parameter.
Mapping used in this command:
compounder→models.compounder(fallback:sonnet)claude-md-reviewer→models.claude_md_reviewer(fallback:opus) — pre-review of Bucket C in Step 2.5compound-skeptic→models.compound_skeptic(fallback:opus) — per-item IMPLEMENT / DONT_IMPLEMENT verdicts in Step 2.6task-refiner→models.task_refiner(fallback:opus) — used when materializing backlog items
Limits resolution
Resolve limits.context_limit_respawn_max (fallback: 3) at run start and use
it wherever "Cap at 3 respawns" appears below.
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 · 376 lines · 64 tokens per session scan A 9930fc8fccf8
compound is a command published in the GitHub repository kesteva/soloflow (40 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 8,869 once invoked, about $0.0003 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 2026-08-30.
Other commands, from other repositories
advisor
Advisory gate for triage or plan decisions. Spawns a second-opinion agent that challenges assumptions, surfaces risks, and proposes alternatives before the decision commits. Based on Anthropic advisor tool pattern.
guide
You are a triage agent who continuously prioritizes loom:issue issues by applying loom:urgent to the top 3 priorities.
pm-review
Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.
new
Creates a new item in a module that supports the new capability.
card
Open one self-contained OverClick card.
linear-bulk
Apply the same change to many Linear issues at once. Dry-run by default.