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 HigorAlves/orc --skill caveman-reviewgit clone --depth 1 https://github.com/HigorAlves/orcWrote 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/higoralves/orc/caveman-review)<a href="https://agentmods.dev/skills/higoralves/orc/caveman-review"><img src="https://agentmods.dev/badge/skills/higoralves/orc/caveman-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/higoralves/orc/caveman-review"><img src="https://agentmods.dev/badge/skills/higoralves/orc/caveman-review.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 | $0.00022 | $0.00781 |
| Opus 5.5 | $0.00009 | $0.00312 |
| Sonnet 5.5 | $0.00004 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
caveman-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 8d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write code review comments terse and actionable. One line per finding. Location, problem, fix. No throat-clearing.
Scope: This skill governs review tone (terse, signal-only, no praise, no nits). For the posting mechanism (inline GitHub PR comments, suggestion blocks, severity-event mapping that prevents "approve while flagging bugs" contradictions) see
orc:inline-review. The two compose: comment bodies follow caveman-review tone; the inline-review skill handles how those bodies get posted.
Rules
Format: L<line>: <problem>. <fix>. — or <file>:L<line>: ... when reviewing multi-file diffs.
Severity prefix (optional, when mixed):
🔴 bug:— broken behavior, will cause incident🟡 risk:— works but fragile (race, missing null check, swallowed error)🔵 nit:— style, naming, micro-optim. Author can ignore❓ q:— genuine question, not a suggestion
Drop:
- "I noticed that...", "It seems like...", "You might want to consider..."
- "This is just a suggestion but..." — use
nit:instead - "Great work!", "Looks good overall but..." — say it once at the top, not per comment
- Restating what the line does — the reviewer can read the diff
- Hedging ("perhaps", "maybe", "I think") — if unsure use
q:
Keep:
- Exact line numbers
- Exact symbol/function/variable names in backticks
- Concrete fix, not "consider refactoring this"
- A
```suggestionblock when the fix is an exact ≤6-line replacement (posting rules perorc:inline-review) — one click beats one paragraph <details>for rationale that must exist but shouldn't dominate the thread- The why if the fix isn't obvious from the problem statement
Examples
❌ "I noticed that on line 42 you're not checking if the user object is null before accessing the email property. This could potentially cause a crash if the user is not found in the database. You might want to add a null check here."
✅ L42: 🔴 bug: user can be null after .find(). Add guard before .email.
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.
- 8d ago Changed · +1 lines · -31 tokens per session d88aba945ec6
- 1mo ago First seen · 55 lines · 53 tokens per session scan A 1f4a2d82d6af
caveman-review is a skill published in the GitHub repository HigorAlves/orc (7 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 781 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 skills, from other repositories
clean-code-cpp
Use when writing or reviewing C++ code — deeper idioms beyond the basics (ownership, noexcept/constexpr discipline, span/stringview, error-handling policy, concrete-before-abstract).
clean-code-c
Use when writing or reviewing C — deeper idioms (ownership discipline, bounded string ops, allocation checking, linkage, initialization) beyond clang-tidy.
clean-code-go
Use when writing or reviewing Go — deeper idioms (error wrapping, small interfaces at the consumer, context, goroutine lifecycle, avoiding interface{}).
clean-code-python
Use when writing or reviewing Python — deeper idioms (type hints, dataclasses/pydantic, no mutable defaults, EAFP, pathlib, context managers, comprehensions).
clean-code-rust
Use when writing or reviewing Rust — deeper idioms (ownership/borrows, error handling with thiserror/anyhow, avoiding unwrap and Rc , iterator style, newtypes).
clean-code-ts
Use when writing or reviewing TypeScript — deeper idioms (eliminate any, discriminated unions, narrowing, exhaustiveness, schema-derived types, async correctness).