swarm-fix

swarm-fix is a command for Claude Code from fozzfut/swarm-suite. It costs 16 tokens per session (532 once invoked), scanned A, original, MIT.

A command for applying fixes to confirmed code-review findings, using an iterative process for changes that may need repeated testing.

In plain words
What is it for?
Fixing high- or medium-severity findings, deciding which need repeated evaluation, and showing the proposed changes.
Why use it?
It helps turn prioritized review findings into code changes while requiring confirmation before fixing selected issues.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Fixing high- or medium-severity findings, deciding which need repeated evaluation, and showing the proposed changes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/fozzfut/swarm-suite/swarm-fix
Install

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.

Clone the repo
git clone --depth 1 https://github.com/fozzfut/swarm-suite

Made for: Claude Code.

Wrote 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.

agentmods badge for swarm-fix

README.md
[![agentmods](https://agentmods.dev/badge/commands/fozzfut/swarm-suite/swarm-fix.svg)](https://agentmods.dev/commands/fozzfut/swarm-suite/swarm-fix)
Your own site
<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>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 532 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash c8c032628d26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

.claude/commands/swarm-fix.md · 31 lines

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:

  1. Call kb_navigator_state(project_path=<cwd>).
  2. Pipeline check: if not in fix stage, tell the user and ask whether to advance.
  3. Find candidates:
    • If $ARGUMENTS is 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.
  4. Show the user the prioritised list (max 5 entries) and confirm: "Fix all of these, or pick a subset?"
  5. 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 in security / 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 just propose_fix once. d. Always show the proposed diff to the user before apply. Never silently apply_approved. e. After the user approves: apply_approved(...) for the consensus fix, or apply_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.
  6. 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_approved if kb_check_quality_gate last returned stop_circuit_breaker -- escalate to user.
  • Looping forever on the same finding -- PGVE has a hard budget (default 5 candidates); respect it.
Changes

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.

  1. 8d ago First seen · 31 lines · 16 tokens per session scan A c8c032628d26

Subscribe to this mod's changes

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.