Borrowing it
Nothing to install: this file belongs to vmihalis/hacker-bob. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vmihalis/hacker-bob/main/.claude/skills/bob-diff-review/SKILL.mdgit clone --depth 1 https://github.com/vmihalis/hacker-bobWrote 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/vmihalis/hacker-bob/bob-diff-review)<a href="https://agentmods.dev/skills/vmihalis/hacker-bob/bob-diff-review"><img src="https://agentmods.dev/badge/skills/vmihalis/hacker-bob/bob-diff-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/vmihalis/hacker-bob/bob-diff-review"><img src="https://agentmods.dev/badge/skills/vmihalis/hacker-bob/bob-diff-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 121 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00100 | $0.03989 |
| Opus 5.5 | $0.00040 | $0.01596 |
| Sonnet 5.5 | $0.00020 | $0.00798 |
| Haiku 4.5 | $0.00010 | $0.00399 |
Grade A, and why
bob-diff-review 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the bob-diff-review pipeline orchestrator. You run headlessly,
invoked by bob-runner.ts. Parse $ARGUMENTS, execute the S2-S6 pipeline
steps in order, and write diff-review-findings.json to --output-dir.
Environment Requirements
The runner environment MUST supply:
- Exactly one Anthropic credential injected by the runner — see
Authentication. The runner spawns this skill inside an
already-authenticated
claudesubprocess, so the skill inherits whichever credential the runner chose (CLAUDE_CODE_OAUTH_TOKENpreferred, orANTHROPIC_API_KEYfallback). The skill does not select auth itself. - No GitHub or package-install tokens.
bob-runner.tsallowlists the child environment and strips workflow inputs, GitHub tokens,BOB_INSTALL_TOKEN, proxy credentials, and unrelated operator secrets before invoking Claude.
No credential value must appear in any log or output file. Do not inspect, print, or shell-check credential environment variables from this skill; the runner is responsible for authenticating the subprocess before invocation.
Authentication
bob-diff-review supports dual auth for the headless claude subprocess:
OAuth-token auth (preferred) and API-key auth (fallback). The runner injects
exactly one credential into the child environment with deterministic
precedence — OAuth wins and the API key is never injected alongside it.
| Credential | Env var the CLI reads | Action input | Workflow secret |
|---|---|---|---|
OAuth token (preferred, from claude setup-token) |
CLAUDE_CODE_OAUTH_TOKEN |
anthropic-oauth-token |
ANTHROPIC_OAUTH_TOKEN |
| API key (pay-per-use fallback) | ANTHROPIC_API_KEY |
anthropic-api-key |
ANTHROPIC_API_KEY |
Runner precedence (single injection, OAuth wins):
- If an OAuth token is present, the runner sets
CLAUDE_CODE_OAUTH_TOKENand does not setANTHROPIC_API_KEYat all. This prevents the API key from silently shadowing OAuth and exhausting credits. - Otherwise (only the API key is present), the runner sets
ANTHROPIC_API_KEYand does not set the OAuth var. - Exactly one credential is injected, never both.
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 · 316 lines · 100 tokens per session scan A 0707513fb44f
bob-diff-review is a skill published in the GitHub repository vmihalis/hacker-bob (100 stars, last pushed 3d ago), licensed Apache-2.0. It adds 100 tokens to every session and 3,989 once invoked, about $0.0004 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 skills, from other repositories
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…
issue-import-from-pr
Open a tracker for a security-relevant fix that already exists as a public PR, with no report. The tracker lands in Assessed with scope, PR-state and remediation fields filled from the PR; pairs with security-cve-allocate.
pre-first-pr-check
Run a newcomer-focused pre-flight checklist on a local branch before opening a PR. Checks CONTRIBUTING conventions, SPDX headers on new files, commit-message shape (including the Generated-by: trailer for AI-assisted work), and the placeholder convention — then returns a structured checklist report. Read-only; no…
quick-merge
Identify trivial, low-risk PRs in the ready for maintainer review queue of that pass every quality gate and touch only supplementary areas (docs, changelog, translations, tests) — the "express lane". Surfaces and ranks candidates with per-PR diff summaries, an all-gates-green attestation, and the exact merge command.…
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
code-review
Review ServiceNow server-side scripts for ES5 violations, ACL/injection/XSS issues, N+1 queries, missing setLimit/error handling, hard-coded sysids, and business-rule recursion risks.