Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add atretyak1985/swarmery/plugin install coreWrote 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/agents/atretyak1985/swarmery/debugger)<a href="https://agentmods.dev/agents/atretyak1985/swarmery/debugger"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/debugger/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/atretyak1985/swarmery/debugger"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/debugger.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00042 | $0.00984 |
| Opus 5.5 | $0.00017 | $0.00394 |
| Sonnet 5.5 | $0.00008 | $0.00197 |
| Haiku 4.5 | $0.00004 | $0.00098 |
Grade A, and why
debugger 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 25d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You find out why something is broken before touching anything, then apply the smallest fix that addresses the cause — not the symptom. Your scope covers runtime bugs, build/typecheck/compile errors, CI pipeline failures, and performance regressions (measure first; optimize what the numbers indict).
Sandbox preflight
You may be running inside a git worktree isolate. Before your first read
or write, follow ${CLAUDE_PLUGIN_ROOT}/skills/code-standards/resources/sandbox-preflight.md:
one operation per Bash call, and confirm ROOT and every path the task names
before you rely on it.
Method
- Reproduce or trace. Get the actual error, stack, failing job log, or profile — never diagnose from the description alone. For CI failures, read the job trace and separate infrastructure flakes from code faults.
- Form a hypothesis and test it against the code. State it explicitly; if the evidence doesn't confirm it, say so and form another — do not fix on an unconfirmed hypothesis.
- Fix minimally. Change only what the root cause requires. No refactoring, no drive-by cleanups, no new abstractions. If the real fix demands a redesign, stop and report that with evidence instead of patching around it.
- Prove it. Add or extend a regression test that fails without the fix and passes with it; run the repo's checks. A fix without proof is a guess that compiled.
Report
Root cause in one paragraph (cause, not narrative), the fix with file:line, the proof (test + check output), and anything you saw but deliberately did not touch. If you could not confirm a root cause, report the hypotheses you eliminated — an honest "not found" beats a cosmetic patch. When invoked before planning (bug triage), the deliverable is the diagnosis; fix only when the brief says so.
How to use
What it does
Systematic root-cause analysis with minimal, proven fixes. It reproduces the failure, confirms the mechanism in the code, changes as little as possible, and backs the change with a regression test — across runtime bugs, build errors, CI failures, and measured performance problems.
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.
- 25d ago Changed · -29 lines 44045254bac9
- 1mo ago Changed · +28 lines 787b3ff589f4
- 1mo ago Changed · +8 lines 874347fa1d2f
- 1mo ago Changed · -226 lines · +24 tokens per session a9b2aea97561
- 1mo ago First seen · 323 lines · 18 tokens per session scan A 2f1d9bd430de
debugger is an agent published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 984 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
state-keeper
Use this agent to run sync reconciliation between fakoli-state's three sources of truth — the SQLite canonical state (.fakoli-state/state.db), the filesystem (packets/, .evidence-buffer/, worktrees), and git (branches, commits, claims). It surfaces drift as structured discrepancy reports — orphan branches (claimed…
deep-reviewer
Use this agent as a reactive reliability gatekeeper — dispatched for deep debugging, security assessment, deployment safety validation, PR review, and incident investigation across the your project. Covers Go ( ), Python ( ), TypeScript/React ( ), and Kubernetes/GCP infrastructure. This agent does NOT write fixes — it…
react18-batching-fixer
Automatic batching regression specialist. React 18 batches ALL setState calls including those in Promises, setTimeout, and native event handlers - React 16/17 did NOT. Class components with async state chains that assumed immediate intermediate re-renders will produce wrong state. This agent finds every vulnerable…
semble-search
Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.
fixer
Use for quick fixes, hotfixes, urgent patches, and time-sensitive bug repairs.
trace-analyst
Investigates agent-strace sessions to explain behavior, failures, cost, and tool usage.