Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Adityaraj0421/naksha-studionpx agentmods add commands/adityaraj0421/naksha-studio/naksha-doctorWrote 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/commands/adityaraj0421/naksha-studio/naksha-doctor)<a href="https://agentmods.dev/commands/adityaraj0421/naksha-studio/naksha-doctor"><img src="https://agentmods.dev/badge/commands/adityaraj0421/naksha-studio/naksha-doctor/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/commands/adityaraj0421/naksha-studio/naksha-doctor"><img src="https://agentmods.dev/badge/commands/adityaraj0421/naksha-studio/naksha-doctor.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 | $0.00014 | $0.02777 |
| Opus 5 | $0.00007 | $0.01388 |
| Sonnet 5 | $0.00003 | $0.00555 |
| Haiku 4.5 | $0.00001 | $0.00278 |
Grade A, and why
naksha-doctor 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 11d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/naksha-doctor
Run a full health check of the naksha plugin — structural validation, metadata consistency, behavioral smoke, and legacy branding guard. Report each check as ✅ PASS or ❌ FAIL with specific remediation for any failures.
Arguments
- No argument: run all checks and show the status report
--fix: after showing failures, output step-by-step remediation instructions for each failed check
Step 1: Locate the plugin root
Use Glob to find meta/stats.json — the directory containing it is the plugin root. All scripts are in scripts/ relative to that root. Change to that directory before running scripts.
Step 2: Run all quality checks
Run each script separately so results can be attributed individually. Capture output and exit code for each:
node scripts/validate-structure.js 2>&1
bash scripts/verify-metadata.sh 2>&1
bash scripts/behavioral-smoke.sh 2>&1
bash scripts/guard-legacy-branding.sh 2>&1
Step 2.5: MCP Availability Check
Probe the two primary MCP integrations that naksha commands depend on. These checks are informational — they reveal whether MCP-dependent commands will work in the current environment. MCP unavailability does not make the plugin unhealthy; it means certain commands will operate in fallback mode.
Playwright MCP:
Attempt to call mcp__plugin_playwright_playwright__browser_navigate with url: "about:blank".
- If the call succeeds → record
AVAILABLE - If the tool throws an error or is not found → record
UNAVAILABLE
Figma MCP:
Attempt to call mcp__figma-console__figma_get_status.
- If the call succeeds → record
AVAILABLE - If the tool throws an error or is not found → record
UNAVAILABLE
Stitch MCP:
Attempt to call mcp__stitch__list_projects.
- If the call succeeds → record
AVAILABLE - If the tool throws an error or is not found → record
UNAVAILABLE
Record all three results for inclusion in the health report.
Step 2.6: Project Memory Check
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.
- 11d ago First seen · 231 lines · 14 tokens per session scan A e09e0ef2ff4d
naksha-doctor is a command published in the GitHub repository Adityaraj0421/naksha-studio (318 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 2,777 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 commands, from other repositories
debug-helper
Use when something is broken and you need it diagnosed. A build failure, a runtime crash, a blank page, an unreadable error message, or behaviour that is simply wrong. Gives one exact fix, not a list of things to try.
error-handling-specialist
Use when things go wrong badly. Error messages that blame the user, validation firing at the wrong moment, form data lost on failure, dead-end 404 and 500 pages, or no way to retry.
run-review
Cross-run review of Design I/O runs — gate table + repeat blockers + rule candidate queue (derived, report-only).
doctor
Diagnose installed design-playbook capability and repairs.
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
battle
Head-to-head graded battle card between two sites — eight dimensions, bar-by-bar, verdict line.