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 skills add ccevans/bobbycode --skill bobby-reviewgit 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/skills/ccevans/bobbycode/bobby-review)<a href="https://agentmods.dev/skills/ccevans/bobbycode/bobby-review"><img src="https://agentmods.dev/badge/skills/ccevans/bobbycode/bobby-review/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/skills/ccevans/bobbycode/bobby-review"><img src="https://agentmods.dev/badge/skills/ccevans/bobbycode/bobby-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.02537 |
| Opus 5.5 | $0.00020 | $0.01015 |
| Sonnet 5.5 | $0.00010 | $0.00507 |
| Haiku 4.5 | $0.00005 | $0.00254 |
Grade A, and why
review-code 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 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.
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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bobby Review Skill
Deep code review. Reads the full context around every change to catch regressions, broken callers, misused APIs, and LLM-typical mistakes. Separate agent from build for fresh perspective.
Pre-flight Checks
- Check learnings — Read
.claude/skills/bobby-review/learnings.md+.claude/skills/bobby-review/learnings.local.mdand.claude/skills/bobby-shared/learnings.md+.claude/skills/bobby-shared/learnings.local.mdin parallel - Branch check —
git branch --show-currentmust NOT be main/master - Hygiene check —
git status --shortshould show no uncommitted source files (build agent left dirty state if it does) - Load context — Read these in parallel:
- The ticket's
ticket.md— acceptance criteria - The ticket's
plan.md— intended approach - The ticket's
test-cases.md— expected test coverage
- The ticket's
- Understand what was built —
git log --oneline main..HEADto see all branch commits
Investigation First
<investigation_rules> Before forming any opinion about the code:
- Read
ticket.mdandplan.mdin parallel — understand what was supposed to be built and the intended approach - Read every file referenced in
plan.mdthat was supposed to change - If the diff touches files not in the plan, read those files to understand why
- Do not approve or reject based on the diff alone — verify against the actual codebase </investigation_rules>
Deep Code Review
This is the core of your job. Don't skim diffs — investigate the code like you're debugging a production incident before it happens.
1. Trace the change boundaries
- Run
git diff main...HEAD --stat— get an overview of every file touched - For each changed file, read the full file (not just the diff hunk) to understand context
- Cross-reference against
plan.md:- Files in the plan that were NOT changed — were they supposed to be?
- Changed files NOT in the plan — why were they touched? Is this scope creep?
2. Check for breakage in callers and dependents
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 Changed · +6 lines 63629bec21dc
- 1mo ago First seen · 202 lines · 50 tokens per session scan A a38d6e0453e5
review-code is a skill published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 2,537 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.
fix-pr
One-verb pipeline for the operator's highest-frequency manual loop: fetch a PR's unresolved reviewer feedback (inline review comments, review-summary bodies, and issue-level conversation comments) and failing CI checks, triage each issue via parallel read-only probes, fix the validated items in an isolated managed…
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
otto-review-remediation
Handle trusted reviewers' change requests on Otto PRs.