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/bugfixgit 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 | $0.00023 | $0.03750 |
| Opus 5 | $0.00012 | $0.01875 |
| Sonnet 5 | $0.00005 | $0.00750 |
| Haiku 4.5 | $0.00002 | $0.00375 |
Grade A, and why
bugfix scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/soloflow:bugfix
You are running the SoloFlow bugfix workflow. The user has reported a bug. Your job is to:
- Identify the bug — spawn the bug-investigator to do read-only root-cause analysis.
- Confirm the hypothesis with the user (unless
--no-confirmis in$ARGUMENTS). - Resolve the bug — spawn the executor with a precise plan derived from the investigation.
- Verify the fix — spawn shadow-verifier; on
NEEDS_CHANGES, retry the executor. - Lock it in — spawn test-writer to add a regression test.
This command is a sibling of /soloflow:quick. Both run a single task inline (no run branch, no worktree, no parallelism, no per-task code review). The difference: /quick assumes the user already knows the fix; /bugfix performs a dedicated investigation step first and gates on user confirmation before any code changes.
The bug report is: $ARGUMENTS
Parse $ARGUMENTS for the optional --no-confirm flag. If present, strip it from the bug report text before passing the rest to the investigator, and skip the confirmation gate in Step 4.
Step 1: Resolve models + limits (cache for the rest of the run)
Run once at the start, cache the result:
node "${CLAUDE_PLUGIN_ROOT}/scripts/config/resolve.js" --all
Keys consumed:
models.bug_investigator(fallback:opus) — the investigator runs Opus by default for judgment.models.executor/models.test_writer(fallback:sonnet)models.verifier(fallback:opus)limits.executor_retry_max(fallback: 3) — cap onNEEDS_CHANGESretries in Step 8.limits.context_limit_respawn_max(fallback: 3) — cap onCONTEXT_LIMITrespawns for any agent.
Reuse the cached values across all agent spawns and respawns. Also cap investigator re-spawns (after INVESTIGATION_INCONCLUSIVE + new user input in Step 3) at 2 — independent of the context-limit budget.
Step 2: Check initialization
If .soloflow/ does not exist, report: "SoloFlow not initialized. Run /soloflow:init first." and stop.
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 · 289 lines · 23 tokens per session scan A 83b7baadcc0e
bugfix is a command published in the GitHub repository kesteva/soloflow (41 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 3,750 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.