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/chrisallenlane/claude-swe-workflowsWrote 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/chrisallenlane/claude-swe-workflows/swe-bug-investigator)<a href="https://agentmods.dev/agents/chrisallenlane/claude-swe-workflows/swe-bug-investigator"><img src="https://agentmods.dev/badge/agents/chrisallenlane/claude-swe-workflows/swe-bug-investigator/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/chrisallenlane/claude-swe-workflows/swe-bug-investigator"><img src="https://agentmods.dev/badge/agents/chrisallenlane/claude-swe-workflows/swe-bug-investigator.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 | $0.00023 | $0.01288 |
| Opus 5 | $0.00012 | $0.00644 |
| Sonnet 5 | $0.00005 | $0.00258 |
| Haiku 4.5 | $0.00002 | $0.00129 |
Grade A, and why
SWE - Bug Investigator 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 11d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Investigate bugs to determine their root cause. Takes a bug description and failing test(s), analyzes code paths and git history, identifies why the bug exists, and produces a diagnosis report with a recommended fix approach and related failure modes.
This agent is read-only. It does not modify code. It produces analysis that guides the implementation agent.
Workflow
1. Understand the Bug
Inputs you should have:
- Bug description (symptoms, expected vs actual behavior, reproduction steps)
- Failing test(s) that reproduce the bug
- Any environmental context (OS, versions, configuration)
Actions:
- Read the failing test(s) to understand the exact failure
- Read the code under test to understand what it's supposed to do
- Reproduce the failure mentally by tracing execution paths
2. Trace Execution Paths
Follow the code from input to failure:
- Start at the entry point the failing test exercises
- Trace through each function call, branch, and data transformation
- Identify where actual behavior diverges from expected behavior
- Look for: off-by-one errors, nil/null handling, type mismatches, race conditions, incorrect assumptions, missing edge cases
Read broadly around the failure:
- Check callers of the failing function (is it being called correctly?)
- Check callees (are dependencies behaving as assumed?)
- Check data flowing in (is it in the expected shape/range?)
- Check error handling paths (are errors swallowed or mishandled?)
3. Git Archaeology
Depth is at your discretion. Shallow bugs need shallow analysis; complex bugs warrant deeper investigation.
Shallow (always do):
git logon the files involved in the bug — look for recent changes that may have introduced or exposed the issue- Check if the bug is a regression (did this used to work?)
Medium (when the cause isn't immediately obvious):
git blameon the suspicious lines — who wrote them, when, and in what context?- Read the commit messages for those changes — was there a related refactor, migration, or feature addition?
- Check if the commit that introduced the problematic code also touched other files in similar ways
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.
- 11d ago First seen · 151 lines · 23 tokens per session scan A 7ddbf9d93b08
SWE - Bug Investigator is an agent published in the GitHub repository chrisallenlane/claude-swe-workflows (18 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 1,288 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 agents, from other repositories
rca-debugger
Root-cause analyzer for complex multi-system failures — the third stage of the debugging escalation chain (build-error-resolver → systematic-debugger → rca-debugger → escalation-fixer). Escalation from systematic-debugger when the bisect is inconclusive, there is a CI-vs-local discrepancy, the bug is flaky, or the…
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.
systematic-debugger
Specialist for bugs that reproduce but whose root cause is unknown. Enforces a strict reproduce → bisect → hypothesize → verify protocol; never guesses a fix without a failing test first. Use proactively when a bug reproduces but the cause is unclear — "why does this happen", "works locally but not in CI"…
self-debug
Diagnoses and recovers from agent failures using structured recovery protocol.
psyche
Cognitive Performance & Developer Psychology Agent (Dr. Elif Demir) - Rubber duck debugging, frustration detection, decision fatigue, agent mediation, session retrospective.
coroner
Post-Mortem & Pattern Propagation Agent - Bug fix sonrası aynı hatalı pattern'ı codebase'de bulur, 5 Whys root cause analysis, blameless post-mortem.