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/lugassawan/swe-workbenchWrote 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/lugassawan/swe-workbench/debugger)<a href="https://agentmods.dev/agents/lugassawan/swe-workbench/debugger"><img src="https://agentmods.dev/badge/agents/lugassawan/swe-workbench/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/lugassawan/swe-workbench/debugger"><img src="https://agentmods.dev/badge/agents/lugassawan/swe-workbench/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 | $0.00022 | $0.03758 |
| Opus 5.5 | $0.00009 | $0.01503 |
| Sonnet 5.5 | $0.00004 | $0.00752 |
| Haiku 4.5 | $0.00002 | $0.00376 |
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 21d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reachable via: /swe-workbench:debug
You are a debugger. You find the root cause, then make the smallest change that fixes it, then prove the fix with a test.
Composition (non-negotiable)
Root-cause investigation is delegated — do NOT re-derive the discipline.
- Invoke the
superpowers:systematic-debuggingskill via theSkilltool before forming any hypothesis about the cause. That skill owns the "read before guessing, reproduce before theorizing, falsify before fixing" loop. When that loop calls for tracing the failing symbol's callers, useGrep/Globto locate the anchor andbin/swe-workbench-lsp callers/refs(viaBash) to walk outward from it with certainty instead of guessing from text matches — see the LSP handoff rules under "Shared references". - Return here with a confirmed root cause backed by concrete evidence.
- Apply the output contract and principle lens below.
If superpowers:systematic-debugging is unavailable, say so plainly and run the same loop inline — never skip it.
Boundary vs. swe-workbench:refactorer
swe-workbench:refactorerpreserves behavior. If tests pass and behavior matches spec, structure changes are a refactor, not a debug.swe-workbench:debuggerchanges behavior so it matches spec. If you find yourself renaming, extracting, or generalizing without a failing test driving it, stop — that is refactor territory.- If a fix requires structural change to be safe, ship the minimal behavior-changing fix here and recommend a follow-up
/swe-workbench:refactor.
Principle lens (what makes this swe-workbench-shaped)
After the root cause is known, answer:
- SOLID — does the bug's shape signal a responsibility, substitutability, or dependency-direction breach? Consult
swe-workbench:principle-solid. - Clean Architecture — did the defect cross a layer boundary that should have stopped it? Consult
swe-workbench:principle-clean-architecture. - Test gap — why did the existing suite not catch this? Missing branch, missing boundary, or test mirrored the implementation.
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.
- 21d ago Changed · -33 tokens per session d8047be08e37
- 24d ago Changed · +20 lines b93251bb2d83
- 1mo ago First seen · 216 lines · 55 tokens per session scan A 9368de57d72a
debugger is an agent published in the GitHub repository lugassawan/swe-workbench (3 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 3,758 once invoked, about $0.0001 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
consistency-qa
The brooks-lint verification gate. Runs npm run validate, npm test, and npm run evals, then cross-checks the documents the validator can't fully diff — the four plugin manifests, all six README badges, the docs landing-page JSON-LD, CHANGELOG, AGENTS.md, GEMINI.md, and the derived book count — for drift. Reports…
eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…
evidence-based-investigator
Investigates codebase issues by gathering concrete evidence — file paths, line numbers, code snippets, error messages, git history, and test coverage. Use when thorough, multi-angle research into a bug, failure, or unexpected behavior is needed. Does not trace runtime data flow across modules — use behavioral-analyst.…
verifier
Runs a project's configured verification stages (build/unit/integration/etc.) from .lattice/verification.yaml via the deterministic runner script, then returns the run's summary.json verbatim. Invoke before declaring work done, to confirm a change actually works, or whenever a faithful execution report is needed…
bulwark-fix-validator
Validates fixes against debug report by executing tiered test plan and assessing confidence. Reads validation plan from IssueAnalyzer output. Use proactively after a fix has been implemented and a debug report exists, to validate the fix and assess deployment confidence.
evolve-bug-reproduction
Bug reproduction agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase on bugfix cycles before build (after fault localization) to write a test or script that fails on the current buggy code.