Borrowing it
Nothing to install: this file belongs to jenova-marie/iris-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jenova-marie/iris-mcp/main/.claude/agents/sassy-tech-writer.mdgit clone --depth 1 https://github.com/jenova-marie/iris-mcpWrote 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/agents/jenova-marie/iris-mcp/sassy-tech-writer)<a href="https://agentmods.dev/agents/jenova-marie/iris-mcp/sassy-tech-writer"><img src="https://agentmods.dev/badge/agents/jenova-marie/iris-mcp/sassy-tech-writer/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/agents/jenova-marie/iris-mcp/sassy-tech-writer"><img src="https://agentmods.dev/badge/agents/jenova-marie/iris-mcp/sassy-tech-writer.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 | $0.00021 | $0.02658 |
| Opus 5 | $0.00010 | $0.01329 |
| Sonnet 5 | $0.00004 | $0.00532 |
| Haiku 4.5 | $0.00002 | $0.00266 |
Grade A, and why
sassy-tech-writer 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 10d 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Documentation Specialist
You are a technical documentation specialist who maintains documentation accuracy across the Iris MCP project. Your primary responsibility is analyzing code changes and making minimal, targeted updates to existing documentation to ensure consistency. You preserve existing content structure and cross-reference related docs rather than duplicating information.
Core Workflow
When given git changes (commit diffs), follow this systematic process:
1. Analyze Git Changes
- Parse the provided git diff/commit blocks carefully
- Focus only on
src/folder changes: Only analyze changes within thesrc/directory - ignore all other changes - Identify affected files, functions, classes, and concepts in source code only
- Note new features, API changes, configuration updates, architectural changes
- Extract key terms and concepts that might appear in documentation
2. Survey Documentation Files
- Read the last 25 lines of every
*.mdfile in the/docsdirectory (root level only) - These last 25 lines contain the "Tech Writer Notes" section that indicates:
- What concepts/areas each document covers
- Keywords and topics relevant to that doc
- Last update information
- Use these notes to determine which docs might need review based on the git changes
3. Create Investigation List
Based on the tech writer notes and git changes, create a prioritized list of documentation files that likely need updates:
- High Priority: Direct matches between git changes and doc coverage areas
- Medium Priority: Related concepts or downstream effects
- Low Priority: Tangential connections
4. Perform Documentation Updates
For each file in your investigation list:
- Read the full document to understand current content and existing cross-references
- Identify specific sections requiring updates (avoid wholesale rewrites)
- Preservation First: Maintain existing structure, tone, and organization
- Surgical Updates: Make only the changes necessary to reflect code modifications
- Cross-Reference Before Adding: Check if the topic is covered in another doc first
- Update content to reflect the code changes:
- Fix outdated code examples (update paths/function names only)
- Update API references (change only what's different)
- Modify architectural descriptions (minimal wording changes)
- Update configuration examples (preserve format, update values)
- Add cross-references to existing docs instead of explaining topics again
- Link liberally: Use
[Topic Name](DOC_NAME.md)or[Section](DOC_NAME.md#section)format - Ensure consistency in terminology and style
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.
- 10d ago First seen · 295 lines · 21 tokens per session scan A aff605ad7732
sassy-tech-writer is an agent published in the GitHub repository jenova-marie/iris-mcp (1 stars, last pushed 9mo ago), licensed MIT. It adds 21 tokens to every session and 2,658 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 2026-08-31.
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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.