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.
npx agentmods add skills/ccevans/bobbycode/bobby-buildnpx skills add ccevans/bobbycode --skill bobby-buildgit clone --depth 1 https://github.com/ccevans/bobbycodeWhat 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 | $0.00054 | $0.01613 |
| Opus 5 | $0.00027 | $0.00807 |
| Sonnet 5 | $0.00011 | $0.00323 |
| Haiku 4.5 | $0.00005 | $0.00161 |
Grade C, and why
build-ticket scanned grade C with 1 finding 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 yesterday.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Never run destructive commands: `rm -rf`, `DROP TABLE`, `git push --force`, `git reset --hard`, `git clean -fd` How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bobby Build Skill
This skill handles implementation using TDD methodology. Commits code to the current branch.
Before Starting
- Check learnings — Read
.claude/skills/bobby-build/learnings.md+.claude/skills/bobby-build/learnings.local.md - Health check — Verify dev environment:
Branch Guard
Before writing any code, check your branch — commits to main bypass review and can break CI:
- Run
git branch --show-current - If on
mainormaster: create a feature branch first:git checkout -b tkt-{ID}(e.g.,tkt-042-add-login)- Use the ticket ID and a short slug from the ticket title
- If already on a feature branch: continue on the current branch
NEVER commit directly to main/master.
Safety Rules
<safety_rules>
- Never run destructive commands:
rm -rf,DROP TABLE,git push --force,git reset --hard,git clean -fd - Only modify files related to this ticket. Check
git diff --statbefore committing. - Do not edit .env files, CI configs, or credentials unless the plan explicitly requires it.
- Do not install global packages or modify system-level configuration. </safety_rules>
Picking Up Work
- Run
git log --oneline -10— understand recent commits, critical on retries to know what's already been built - Read the ticket's
ticket.md,plan.md, andtest-cases.mdin parallel - Check for rejection comments — if this is a retry, read the rejection feedback first
Investigation First
<investigation_rules> Before writing any code:
- Read every file referenced in
plan.mdbefore modifying it — so you implement what was planned, not your own interpretation - If the ticket references a specific function, class, or component, open and read that file first
- When fixing a bug, reproduce it first and read the relevant code path end-to-end
- Read multiple related files in parallel when possible to minimize round-trips
- If you are unsure how an existing module works, read it rather than guessing </investigation_rules>
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 163 lines · 54 tokens per session scan C 1101e43b5f3f
build-ticket is a skill published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 8d ago), licensed MIT. It adds 54 tokens to every session and 1,613 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
haiku
When writing a haiku for this bot, follow these conventions.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.