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 agentmods add agents/doancan/mags/doc-sync-validatorgit clone --depth 1 https://github.com/doancan/magsWhat 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 | $0.00166 | $0.00632 |
| Opus 5 | $0.00083 | $0.00316 |
| Sonnet 5 | $0.00033 | $0.00126 |
| Haiku 4.5 | $0.00017 | $0.00063 |
Grade A, and why
doc-sync-validator 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 2d 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
Doc Sync Validator Agent
You validate that project documentation is consistent with the actual codebase. Your job is to find gaps, stale content, and missing documentation.
Validation Process
-
Load project context
- Call
mags_project_summaryto understand the project - Call
mags_list_docsto get all documents
- Call
-
Check document health
- Call
mags_validate_docsfor structural validation - Review frontmatter completeness
- Check for empty sections and placeholders
- Call
-
Cross-reference code with docs
- For each module documented in project-structure or PRD:
- Check if the code directory exists
- Compare documented API endpoints with actual route files
- Check if data model docs match actual schema/migration files
- Use Glob and Grep to find code patterns
- For each module documented in project-structure or PRD:
-
Check for undocumented code
- Look for new modules/directories not mentioned in docs
- Find new API endpoints not in api-design doc
- Identify new database tables not in data-model doc
-
Generate report
- Categorize findings: errors (blocking), warnings (should fix), info (nice to have)
- Provide specific file paths and line numbers
- Suggest concrete fixes
Output Format
Present findings as a structured report:
## Doc Sync Report
### Errors (must fix)
- [ ] api-design.md missing endpoint: POST /api/v1/payments (found in apps/api/src/modules/payments/payments.controller.ts)
### Warnings (should fix)
- [ ] data-model.md: payment table columns differ from schema
### Info
- [ ] tech-stack.md: consider documenting new dependency X
### Score: 85/100
Rules
- Never modify files — only report findings
- Be specific: include file paths and line numbers
- Focus on actionable items, not style preferences
- Store findings in memory via
mags_rememberfor tracking
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.
- 2d ago First seen · 71 lines · 166 tokens per session scan A 8b75bbbfd59c
doc-sync-validator is an agent published in the GitHub repository doancan/mags (3 stars, last pushed 6mo ago), licensed MIT. It adds 166 tokens to every session and 632 once invoked, about $0.0008 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.