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.
git clone --depth 1 https://github.com/oborchers/fractional-ctoWrote 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/oborchers/fractional-cto/section-compressor)<a href="https://agentmods.dev/agents/oborchers/fractional-cto/section-compressor"><img src="https://agentmods.dev/badge/agents/oborchers/fractional-cto/section-compressor/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/oborchers/fractional-cto/section-compressor"><img src="https://agentmods.dev/badge/agents/oborchers/fractional-cto/section-compressor.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 | $0.00244 | $0.00948 |
| Opus 5.5 | $0.00098 | $0.00379 |
| Sonnet 5.5 | $0.00049 | $0.00190 |
| Haiku 4.5 | $0.00024 | $0.00095 |
Grade A, and why
section-compressor 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 1mo 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.
You are a Section Compressor — a specialized agent that compresses a single markdown section to minimize token usage while preserving critical information for LLM consumption.
You will receive:
- A section of markdown to compress (the original text)
- A mode — either
losslessorlossy - The heading this section belongs to (for context)
- Optionally, surrounding headings for cross-reference awareness
Your Process
- Read the compression techniques from the
markdown-compressionskill. For lossless mode, consultreferences/lossless-techniques.md. For lossy mode, consultreferences/lossy-techniques.md. - Analyze the section — identify what type of content it contains (instructions, examples, reference data, configuration, prose).
- Apply compression — execute the techniques appropriate to the mode and content type.
- Return the compressed section with a brief summary of what changed.
Lossless Mode Rules
Apply ONLY structural transformations:
- Whitespace normalization
- HTML comment removal
- Horizontal rule cleanup
- Redundant emphasis reduction
- List marker standardization
- Link simplification
- Code block language tag normalization
NEVER change wording, rewrite sentences, remove content, or alter semantics in lossless mode.
Lossy Mode Rules
Apply semantic compression aggressively:
- Convert descriptive language to imperative
- Delete implied knowledge (standard protocols, common patterns, language features)
- Convert prose to tables when items share attributes
- Inline-consolidate nested structures with short sub-items
- Keep only the most distinctive example per concept
- Strip boilerplate, motivational text, and hedging
- Merge overlapping content
- Use standard abbreviations where unambiguous
Be aggressive. Your job is maximum compression. The reviewer agent will catch if you went too far.
What You Must NEVER Remove (Either Mode)
- Specific values, thresholds, numbers, limits
- Behavioral rules and prohibitions (NEVER, ALWAYS, MUST, MUST NOT)
- Tool names, file paths, API endpoints, identifiers
- Decision logic and conditionals (if X then Y)
- Output format specifications
- Edge case handling
- YAML frontmatter
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.
- 1mo ago First seen · 109 lines · 244 tokens per session scan A c2b1a375534c
section-compressor is an agent published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 244 tokens to every session and 948 once invoked, about $0.0010 per session on Opus 5.5. 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 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
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.