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 singhharsh1708/kitbash --skill prereviewgit clone --depth 1 https://github.com/singhharsh1708/kitbashWrote 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/singhharsh1708/kitbash/prereview)<a href="https://agentmods.dev/skills/singhharsh1708/kitbash/prereview"><img src="https://agentmods.dev/badge/skills/singhharsh1708/kitbash/prereview/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/singhharsh1708/kitbash/prereview"><img src="https://agentmods.dev/badge/skills/singhharsh1708/kitbash/prereview.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 | $0.00000 | $0.00386 |
| Opus 5.5 | $0.00000 | $0.00154 |
| Sonnet 5.5 | $0.00000 | $0.00077 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
prereview 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.
What it actually says
Review the current diff against this team's conventions and invariants before it ships. Invoke with /prereview before opening a PR, or run as a pre-push gate.
Procedure
- Collect the diff under review: staged changes if any, otherwise the branch diff against the default branch. Review only lines in the diff.
- If a plan artifact exists at {{artifact.plan}}, read it: the review must check the diff against the plan's stated intent and flag unexplained divergence.
- First pass — correctness only: bugs, unhandled failure paths, concurrency hazards, security issues. For each finding, construct the concrete failure scenario (inputs/state → wrong outcome). Discard findings without one.
- Second pass — team standards. Check the diff against each entry in:
{{lore.conventions}}
{{lore.invariants}}
A convention finding MUST cite the convention id. Never report a style opinion that lacks a lore citation.
5. Write findings to .kitbash/artifacts/findings.json (findings@1 schema), most severe first: file, line, severity (high/medium/low), summary (one sentence), scenario, convention (id or null).
6. Report to the user: one line per finding — path:line severity: defect. fix. No praise, no summaries of what the code does, no findings outside the diff.
Gate mode
When run as a gate, exit nonzero if any finding has severity high. The verdict comes from the artifact contents, not prose.
Boundaries
- Do not fix anything unless explicitly asked; report only.
- If the diff exceeds what you can review honestly, review file-by-file and state which files got a shallower pass.
- If there are no lore conventions yet, say so once and proceed with the correctness pass only.
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.
- 1mo ago First seen · 27 lines · 0 tokens per session scan A c27dd3a5ad81
prereview is a skill published in the GitHub repository singhharsh1708/kitbash (9 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 386 tokens. 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
review-agent-work
Review the changes a CodeAgent session made, and open or review a pull request when the user asks.
umbra-trust-review
Verify AI-generated code before shipping. Run Umbra's Trust Score scan before committing or finishing any coding task, treat findings as blocking issues, and re-scan until clean. Use when finishing a task, before a commit, or when reviewing code written by an agent.
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.