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 review-contractgit 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/review-contract)<a href="https://agentmods.dev/skills/higoralves/orc/review-contract"><img src="https://agentmods.dev/badge/skills/higoralves/orc/review-contract/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/review-contract"><img src="https://agentmods.dev/badge/skills/higoralves/orc/review-contract.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 | $0.00027 | $0.01469 |
| Opus 5.5 | $0.00011 | $0.00588 |
| Sonnet 5.5 | $0.00005 | $0.00294 |
| Haiku 4.5 | $0.00003 | $0.00147 |
Grade A, and why
review-contract 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 4d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review contract
One schema, one severity vocabulary, one event rule — defined here and only
here. Reviewer agents preload this skill; the posting layer (orc:inline-review)
and any new reviewer agent reference it instead of restating it.
Finding schema
Reviewer agents return strict JSON only (no surrounding markdown, no prose preamble):
{
"summary": "≤ 2 sentences, ~40 words: one clause on what the PR does + finding counts by severity. Informational only — does NOT decide the event.",
"findings": [
{
"path": "src/auth.ts",
"line": 42,
"start_line": null,
"side": "RIGHT",
"severity": "bug",
"title": "Null deref when token absent",
"body": "When `req.headers.authorization` is missing, `parseToken()` returns null and the next line dereferences `.userId` unconditionally — 500 to client, no log. Guard with an early return.",
"suggestion_code": "const token = parseToken(req);\nif (!token) return res.status(401).end();",
"confidence": 0.92
}
]
}
Zero findings: {"summary": "No actionable issues found. …", "findings": []} —
the posting layer computes APPROVE from the empty list.
Field semantics
- Required per finding:
path,line,severity,title,body,confidence. - Optional:
start_line(multi-line spans:start_line: 45, line: 47; elsenull),suggestion_code(see gate below; elsenull). path— repo-relative POSIX path. NOT a URL, NOTa/- orb/-prefixed. In workspace mode, still repo-relative; the orchestrator prefixes[repo:<name>].line— line number in the NEW file (post-change), computed from the diff hunk header@@ -OLD,N +NEW,N @@plus offset within the hunk. NOT the hunk offset.side— always"RIGHT"(the new/changed code).title— ≤ 80 chars, one line.body—orc:caveman-reviewtone: terse, actionable, signal-only.confidence— 0–1. Drop the finding entirely if < 0.8. A noisy review burns the author's time; false positives erode trust faster than misses.
What ships with it
1 file 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.
- 4d ago Changed · +5 lines · -21 tokens per session 00ab4c5141e2
- 1mo ago First seen · 108 lines · 48 tokens per session scan A 0ca7bf8bd68c
review-contract is a skill published in the GitHub repository HigorAlves/orc (7 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,469 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 2026-09-03.
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-go
Use when writing or reviewing Go — deeper idioms (error wrapping, small interfaces at the consumer, context, goroutine lifecycle, avoiding interface{}).
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).
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-python
Use when writing or reviewing Python — deeper idioms (type hints, dataclasses/pydantic, no mutable defaults, EAFP, pathlib, context managers, comprehensions).