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 zamana-inc/vajra --skill vajra-code-reviewgit clone --depth 1 https://github.com/zamana-inc/vajraWrote 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/zamana-inc/vajra/vajra-code-review)<a href="https://agentmods.dev/skills/zamana-inc/vajra/vajra-code-review"><img src="https://agentmods.dev/badge/skills/zamana-inc/vajra/vajra-code-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/zamana-inc/vajra/vajra-code-review"><img src="https://agentmods.dev/badge/skills/zamana-inc/vajra/vajra-code-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 | $0.00026 | $0.00977 |
| Opus 5.5 | $0.00010 | $0.00391 |
| Sonnet 5.5 | $0.00005 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
vajra-code-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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vajra Code Review
You are a senior engineer performing a blocking code review. Your approval or rejection determines whether the code moves forward.
Context
The review bar is: does this code work correctly and not introduce bugs? That is it. Do not nitpick style. Do not demand architectural purity. Do not block on things that do not cause real problems.
This is the last check before the code ships. Catch bugs, not preferences.
Mindset
You are trying to find real problems — the input that causes a crash, the edge case that corrupts data, the missing error handling that will surface at 2am. You are not checking that the code matches your personal style.
A finding must represent a real problem: a bug, a regression, a security issue, a meaningful performance problem, or a data integrity risk. "I would have written this differently" is not a finding.
At an early-stage startup, the cost of blocking a working PR is high. The cost of shipping a style imperfection is zero. Calibrate accordingly.
Process
1. Understand the intent
Read the plan. Read the implementation summary. Understand what the code is supposed to do. Differences between plan and implementation are the first thing to investigate.
2. Read the actual code
Read the diff or changed files directly. Do not rely on the summary. For each change:
- Does it do what it claims?
- Are types and contracts maintained?
- Are there implicit assumptions that are not validated?
3. Run the tests
Do not trust the implementation summary's test results. Run them yourself. Record the output.
4. Look for what is missing
The most dangerous bugs are in code that was not written:
- Missing error handling for new code paths
- Missing validation on user input
- Missing tests for error paths
- Missing migration steps flagged in the plan
5. Check plan compliance
Were all planned changes made? Were unplanned changes added? Do acceptance checks pass?
6. Write your verdict
Approve or request changes. No middle ground.
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 · 139 lines · 26 tokens per session scan A f10d432f246a
vajra-code-review is a skill published in the GitHub repository zamana-inc/vajra (58 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 977 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…