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.
git clone --depth 1 https://github.com/kesteva/soloflowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/kesteva/soloflow/sprint-and-compound)<a href="https://agentmods.dev/commands/kesteva/soloflow/sprint-and-compound"><img src="https://agentmods.dev/badge/commands/kesteva/soloflow/sprint-and-compound.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00000 | $0.02196 |
| Opus 5 | $0.00000 | $0.01098 |
| Sonnet 5 | $0.00000 | $0.00439 |
| Haiku 4.5 | $0.00000 | $0.00220 |
Grade A, and why
sprint-and-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 8d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/soloflow:sprint-and-compound
Phases 3 + 6 of the SoloFlow pipeline in a single command. Runs /soloflow:sprint to the end of sprint verification, then runs /soloflow:compound on the just-finished sprint before the merge-choice prompt fires, then resumes sprint to the merge prompt + close. Compound's per-item commits land on the same run branch, so the merge-choice prompt at the end decides the fate of both the executed task work AND the applied learnings together — one decision, one branch.
Arguments: $ARGUMENTS (same as /soloflow:sprint — optional task IDs / IDEA-NNN filter, plus --quick / --no-code-review / --no-verification flags). Compound takes no arguments here — the just-finished sprint ID is captured from sprint's payload.
Interleaved flow
Sprint Steps 0.4 → 1.5 → setup prompts (branching, scope, exec mode, dev-server)
Steps 2 → 3.7 → autonomous: execution + verify + sprint verifier
+ sprint-code-reviewer (writes findings file)
↓
Compound Steps 0 → 5 → reads findings, applies approved A/B/C items on the SAME
run branch. With compound.skeptic.auto_accept_verdicts: true,
A/B/C are fully autonomous; Bucket D (tester mode) always
prompts the user with its inline write-up. Compound's Step 6
report is suppressed — folded into the combined report below.
↓
Sprint Step 4 → human review for stuck / human-needed / deferred items
(only interactive if such tasks exist)
Steps 4.4 → 4.6 → merge-choice prompt → sprint-closer finalize → stop dev server
↓
Combined report → sprint stats + compound stats
For maximum autonomy, set compound.skeptic.auto_accept_verdicts: true in .soloflow/config.json (or via /soloflow:config → Operations → Compound). Compound's buckets A/B/C then apply without prompting. Bucket D (tester-mode SoloFlow self-improvement feedback) always prompts the user with its inline write-up — that channel is for a maintainer to read and must not be auto-archived. Without auto_accept_verdicts, compound's Step 3 still prompts per-bucket between sprint verification and the merge choice; the flow is correct but not autonomous.
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.
- 8d ago First seen · 117 lines · 0 tokens per session scan A 2237c2727111
sprint-and-compound is a command published in the GitHub repository kesteva/soloflow (40 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,196 tokens. 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
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.