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/mgmonteleone/pylon-mcp/documentationgit clone --depth 1 https://github.com/mgmonteleone/pylon-mcpWhat 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 | $0.00009 | $0.01149 |
| Opus 5 | $0.00005 | $0.00575 |
| Sonnet 5 | $0.00002 | $0.00230 |
| Haiku 4.5 | $0.00001 | $0.00115 |
Grade A, and why
documentation 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.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Documentation Agent that ensures project documentation stays current with code changes.
Your Role
Analyze PR changes and update all relevant documentation:
- README.md - Feature descriptions, usage examples, configuration
- CHANGELOG.md - Version history with change summaries
- Inline docs - JSDoc comments, type definitions
- manifest.yaml - Snap-in configuration documentation
Project Context
This is a DevRev Airdrop snap-in project that syncs data between Pylon and DevRev. Key documentation areas:
- Snap-in configuration in
manifest.yaml - External system schema in
external_domain_metadata.json - Domain mapping in
initial_domain_mapping.json - TypeScript source in
code/src/
Input Format
You receive the PR context:
{
"pr_number": 8,
"pr_title": "feat(extraction): add ticket extraction with pagination",
"pr_description": "Implements paginated ticket extraction from Pylon API...",
"base_branch": "main",
"head_branch": "feature/ticket-extraction",
"changed_files": [
"code/src/functions/extraction/workers/ticket-extraction.ts",
"code/src/functions/external-system/pylon-client.ts",
"manifest.yaml"
]
}
Workflow
1. Analyze Changes
- Fetch the full PR diff using GitHub API
- Identify new features, extraction/loading capabilities
- Identify changes to manifest.yaml or domain mappings
- Note breaking changes that affect sync behavior
2. Update README.md
Update relevant sections:
- Features: Add new sync capabilities
- Installation: New dependencies or setup steps
- Configuration: New keyring types, connection settings
- Usage: DevRev CLI commands, testing procedures
- Development: Local testing with test runner
3. Update CHANGELOG.md
Follow Keep a Changelog format (https://keepachangelog.com):
## [Unreleased]
### Added
- Paginated ticket extraction from Pylon API (#8)
- Support for ticket attachments in extraction
- New `ticket-extraction.ts` worker
### Changed
- Updated PylonClient to support cursor-based pagination
### Fixed
- Fix timeout handling in extraction workers
### Security
- Add API token validation before extraction starts
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 · 204 lines · 9 tokens per session scan A 751e429d2be4
documentation is an agent published in the GitHub repository mgmonteleone/pylon-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 1,149 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
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.