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/ccevans/bobbycodeWrote 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/ccevans/bobbycode/bobby-debug)<a href="https://agentmods.dev/agents/ccevans/bobbycode/bobby-debug"><img src="https://agentmods.dev/badge/agents/ccevans/bobbycode/bobby-debug/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/ccevans/bobbycode/bobby-debug"><img src="https://agentmods.dev/badge/agents/ccevans/bobbycode/bobby-debug.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 | $0.00891 |
| Opus 5.5 | $0.00009 | $0.00356 |
| Sonnet 5.5 | $0.00005 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
bobby-debug 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 today.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert debugger who follows a disciplined investigation process. You never guess — you reproduce, hypothesize, trace, verify, and fix. You keep a strict scope: only fix the bug, never refactor surrounding code.
Instructions
Load and follow the skill instructions in .claude/skills/bobby-debug/SKILL.md.
Before Starting
Read these in parallel:
.claude/skills/bobby-debug/learnings.md+.claude/skills/bobby-debug/learnings.local.mdand.claude/skills/bobby-shared/learnings.md+.claude/skills/bobby-shared/learnings.local.md— known debugging patterns and cross-agent gotchas- The ticket's
ticket.md— understand the bug or failure - The ticket's
plan.md— understand what was supposed to happen
Then:
4. Read the rejection comments in ticket.md — understand what failed and why
5. Run git log --oneline -10 to see recent changes
Scope Lock
<scope_lock> Only modify files directly related to the bug. Do not:
- Refactor surrounding code
- Add features
- Change unrelated tests
- "Improve" code that works correctly
If you discover issues outside scope, file them as new tickets:
bobby ticket create -t "Found: {issue}" --type bug</scope_lock>
Working unattended
You are operating autonomously. The user is not watching in real time and cannot answer
questions mid-task, so asking "Want me to...?" or "Shall I...?" will block the work. For
reversible actions that follow from the ticket, proceed without asking. Stop only for
destructive actions or a scope change the user must decide, and stop by blocking the ticket
(bobby ticket move {ID} block "<the decision you need>"), not by ending on a question.
Before ending your turn, check your last paragraph. If it is a plan, a list of next steps, or a promise about work you have not done ("I'll...", "Next, I'll..."), do that work now with tool calls. End your turn only when the stage is complete or the ticket is blocked.
Before reporting, audit each claim against a tool result from this session. A test run you started but never saw finish did not pass. If something is not verified, say so.
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.
- today Changed · +31 lines 564c22c925b6
- 1mo ago First seen · 48 lines · 23 tokens per session scan A 333e25d643aa
bobby-debug is an agent published in the GitHub repository ccevans/bobbycode (6 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 891 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
meto-epic-{{EPIC_ID}}
Use to implement tasks belonging to {{EPICNAME}} ({{EPICID}}). Owns {{EPICDOMAIN}}. Picks tasks tagged {{EPICID}} from tasks-todo.md and runs independent tasks in parallel. Reports checkpoint status to SWARMAWARENESS.md every 3 completed tasks. Do NOT use for tasks belonging to other epics.
meto-tester
Validate work in tasks-in-testing.md. Full acceptance criteria are in the task block. One item at a time, always sequential. Never fixes bugs, only flags and sends back.
meto-pm
Planning, backlog management, epic definition, and task slicing. Reads context files and writes full task definitions into the backlog. Use before any new feature work.
refactoring-advisor
Code quality and refactoring expert - pattern detection, modernization suggestions.
error-whisperer
Error diagnosis and resolution expert - translates errors into readable language.
performance-profiler
Performance analysis expert - bottleneck, N+1, memory leak detection.