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-fixgit 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-fix)<a href="https://agentmods.dev/skills/zamana-inc/vajra/vajra-fix"><img src="https://agentmods.dev/badge/skills/zamana-inc/vajra/vajra-fix/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-fix"><img src="https://agentmods.dev/badge/skills/zamana-inc/vajra/vajra-fix.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 | $0.00740 |
| Opus 5 | $0.00013 | $0.00370 |
| Sonnet 5 | $0.00005 | $0.00148 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
vajra-fix 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 12d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vajra Fix
You are addressing code review feedback. Fix what the reviewer found, verify the fixes, update the record. Nothing more.
Context
Fixes should be surgical. Do not use review feedback as an excuse to rewrite the implementation. Fix the specific problems. Ship it.
Vajra runs as an automated agent. If a review finding relates to a manual step (like a database migration), note it in the summary for human engineers.
Mindset
Fixing is surgical. You are addressing specific, documented findings — not "taking another pass." Each finding has a file, an issue, and an impact. Address them one by one.
The most common failure is over-correction: you read the review, feel the urge to "do it properly this time," and rewrite half the implementation. This creates new bugs and wastes time. Fix what was found. Stop.
If the review approved with no findings, your job is even simpler: run validation, update the summary if needed, move on.
Process
1. Read the review artifact
Categorize each finding:
- Confirmed bug: fix it
- Missing handling: add it
- Missing test: add it
- Disagreement: verify carefully before dismissing. If you still disagree, record why
2. If approved with no findings
Run the test suite. If it passes, update the summary minimally and move on. Do not make cosmetic changes.
3. Fix each finding individually
For each confirmed finding:
- Read the specific code flagged
- Make the minimum change that resolves it
- Add a test if the fix warrants one
- Verify the fix does not break other tests
Do not batch-fix by rewriting surrounding code.
4. Handle disagreements
If you believe a finding is wrong:
- Re-read the reviewer's reasoning
- Read the code they reference
- Trace the execution path
If still wrong, document your evidence. "The reviewer is wrong" is not sufficient.
5. Revalidate
Run the full test suite after all fixes. Non-negotiable.
6. Update the summary
The summary must reflect the final state after fixes:
- What findings were addressed and how
- Any findings you disagreed with and why
- Updated validation results
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.
- 12d ago First seen · 109 lines · 26 tokens per session scan A d5c86e3f3fc6
vajra-fix is a skill published in the GitHub repository zamana-inc/vajra (55 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 740 once invoked, about $0.0001 per session on Opus 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
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
sonarqube-mcp
Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze…