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/quickgit 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 | $0.00015 | $0.03156 |
| Opus 5 | $0.00008 | $0.01578 |
| Sonnet 5 | $0.00003 | $0.00631 |
| Haiku 4.5 | $0.00002 | $0.00316 |
Grade A, and why
quick 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/soloflow:quick
You are running the SoloFlow quick bugfix workflow. The user has described a bug or small fix. Your job is to create an inline plan, execute it, and verify the result.
The bug description is: $ARGUMENTS
Model + limits resolution
Run once at the start, cache the result:
node "${CLAUDE_PLUGIN_ROOT}/scripts/config/resolve.js" --all
Keys consumed:
models.executor/models.test_writer(fallback:sonnet)models.verifier(fallback:opus)limits.executor_retry_max(fallback: 3) — cap onNEEDS_CHANGESretries in Step 7limits.context_limit_respawn_max(fallback: 3) — cap onCONTEXT_LIMITrespawns
Reuse the cached values across all agent spawns and respawns.
Step 1: Check initialization
If .soloflow/ does not exist, report: "SoloFlow not initialized. Run /soloflow:init first." and stop.
Step 1.5: Investigation-shape check
Before grounding the bug or doing any Grep/Glob work, classify $ARGUMENTS as one of:
- Fix-shape — the user names a specific file, function, line, value, or describes a mechanical change. Examples:
"fix typo in README line 42","change FOO_TIMEOUT from 30 to 60 in src/config.ts","remove unused import in lib/foo.ts","deps out of date — run npm update","login is broken because the JWT clock skew exceeds 30s — bump the tolerance to 60s in src/auth/jwt.ts". → Proceed to Step 2. - Investigation-shape — the user describes symptoms, error messages, or unexpected behaviors without identifying the root cause or naming a specific change. Examples:
"login button doesn't work on mobile","API returns 500 sometimes","tests are flaky","dropdown closes too early", bare"login is broken". → Stop and redirect (see below). - Ambiguous — proceed to Step 2. Bias toward proceeding: false positives (blocking a legitimate
/quickrun) hurt the user more than false negatives (running/quickon a bug report; Step 3's "too vague to plan" branch will catch most of those before any executor spawn).
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 · 213 lines · 15 tokens per session scan A b71e1b38ddde
quick is a command published in the GitHub repository kesteva/soloflow (41 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 3,156 once invoked, about $0.0001 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
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.
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.