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/fozzfut/swarm-suiteWrote 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/fozzfut/swarm-suite/swarm-fix)<a href="https://agentmods.dev/commands/fozzfut/swarm-suite/swarm-fix"><img src="https://agentmods.dev/badge/commands/fozzfut/swarm-suite/swarm-fix.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 | $0.00016 | $0.00532 |
| Opus 5 | $0.00008 | $0.00266 |
| Sonnet 5 | $0.00003 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
swarm-fix 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.
What it actually says
You are in Swarm Suite navigator mode. The user typed /swarm-fix $ARGUMENTS. The $ARGUMENTS (if any) names a specific finding ID; if empty, work through all confirmed findings in priority order.
Do this:
- Call
kb_navigator_state(project_path=<cwd>). - Pipeline check: if not in
fixstage, tell the user and ask whether to advance. - Find candidates:
- If
$ARGUMENTSis a finding ID: that's the target. - Else:
kb_search_findings(severity=high, status=confirmed) + (medium, confirmed). Sort by severity DESC, then by confidence DESC.
- If
- Show the user the prioritised list (max 5 entries) and confirm: "Fix all of these, or pick a subset?"
- For each finding to fix:
a. Snapshot tests once at the start:
snapshot_tests(session_id). b. Open or reuse a fix session:start_session(review_session=..., arch_session=...). c. Decide PGVE vs one-shot: if the finding is insecurity/threading-safety/error-handling(high-iteration-risk categories), drive PGVE --kb_start_pgve(task_spec=<concise description>)then submit_candidate / evaluate_candidate cycle until accepted or budget exhausted. Otherwise justpropose_fixonce. d. Always show the proposed diff to the user before apply. Never silentlyapply_approved. e. After the user approves:apply_approved(...)for the consensus fix, orapply_single(...)for an individual one. f. After each fix iteration:kb_check_quality_gate(...). Surface the recommendation:continue-- offer next finding.stop_clean-- offer to advance to verify stage.stop_circuit_breaker-- STOP, tell user the cycle is unstable and recommend manual review.
- Once done, end with: "Fixes applied -- want to run verify next?"
Anti-patterns to avoid:
- Applying any fix without showing the diff first.
- Calling
apply_approvedifkb_check_quality_gatelast returnedstop_circuit_breaker-- escalate to user. - Looping forever on the same finding -- PGVE has a hard budget (default 5 candidates); respect it.
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 · 31 lines · 16 tokens per session scan A c8c032628d26
swarm-fix is a command published in the GitHub repository fozzfut/swarm-suite (1 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 532 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.