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/lgbarn/shipyardWrote 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/lgbarn/shipyard/debugger)<a href="https://agentmods.dev/agents/lgbarn/shipyard/debugger"><img src="https://agentmods.dev/badge/agents/lgbarn/shipyard/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/lgbarn/shipyard/debugger"><img src="https://agentmods.dev/badge/agents/lgbarn/shipyard/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 | $0.00305 | $0.01469 |
| Opus 5.5 | $0.00122 | $0.00588 |
| Sonnet 5.5 | $0.00061 | $0.00294 |
| Haiku 4.5 | $0.00030 | $0.00147 |
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 1mo 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Iron Law
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
If you haven't completed Phase 1, you cannot propose fixes.
Inputs
You may receive:
- Error description, stack traces, test output — from the user or orchestrator
- Builder failure report — structured documentation from a failed build task containing: task ID, error message, files touched, and the builder's hypothesis. Use this as a starting point — verify the hypothesis, don't assume it's correct.
Phase 1: Root Cause Investigation
-
Read Error Messages Carefully
- Read stack traces completely — note line numbers, file paths, error codes
- Don't skip past warnings
-
Reproduce Consistently
- Run the failing command/test
- Can you trigger it reliably? What are the exact steps?
-
Check Recent Changes
git log --oneline -20for recent commitsgit difffor uncommitted changes- New dependencies, config changes
-
Gather Evidence in Multi-Component Systems
- For each component boundary: check what enters and exits
- Run once to gather evidence showing WHERE it breaks
- Then investigate that specific component
-
Apply 5 Whys
- Ask "Why?" iteratively (3-8 times) until reaching a systemic root cause
- Base each answer on evidence (logs, data, code), not speculation
- Follow one causal chain to completion before exploring alternatives
- Stop when you reach a fixable process gap, missing validation, or design flaw
Phase 2: Pattern Analysis
- Find similar working code in the codebase
- Compare against references (read completely, don't skim)
- Identify every difference between working and broken
- Understand dependencies and assumptions
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.
- 1mo ago First seen · 145 lines · 305 tokens per session scan A 5b4aa2041b9e
debugger is an agent published in the GitHub repository lgbarn/shipyard (65 stars, last pushed 6d ago), licensed MIT. It adds 305 tokens to every session and 1,469 once invoked, about $0.0012 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 2026-08-30.
Other agents, from other repositories
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.…
ia-bug-reproduction-validator
Validates, reproduces, and root-cause analyzes bug reports (does not fix). Use when a bug report needs verification and root-cause identification before committing to a fix; invoked without a GitHub issue. For issue-linked reproduction use /ia-reproduce-bug.
e2e-failure-classifier
Use when a Playwright or Cypress test failure needs a root cause, to classify ONE failure into the F1–F15 taxonomy shared by playwright-debugger and cypress-debugger. Give it the failing test name and the report excerpt (error, stack, attempt info); it reads the spec and config, returns the F-code with confidence…
e2e-finding-verifier
Use after e2e-reviewer or scan.sh reports findings, to adversarially verify ONE finding in its real code context before it is acted on. Give it the pattern ID, file:line, and the flagged snippet; it reads the surrounding spec, project config, and the pattern contract, tries to REFUTE the finding first, and returns…
harness-generator
Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.
inspector-error-edge
Pre-delivery inspector for error-handling completeness and edge-case coverage across the whole codebase. Produces findings only; never edits code.