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/commands/oborchers/fractional-cto/compress)<a href="https://agentmods.dev/commands/oborchers/fractional-cto/compress"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/compress/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/oborchers/fractional-cto/compress"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/compress.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 | $0.00027 | $0.01649 |
| Opus 5.5 | $0.00011 | $0.00660 |
| Sonnet 5.5 | $0.00005 | $0.00330 |
| Haiku 4.5 | $0.00003 | $0.00165 |
Grade A, and why
compress 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compress the specified markdown file using the markdown-compression skill. The goal is to reduce token usage while preserving the information an LLM needs.
Follow this process exactly:
Step 1: File Validation
Read the file specified in $ARGUMENTS. If no file was provided, use AskUserQuestion to ask the user which file to compress.
Verify:
- File exists and is readable
- File is markdown (
.mdextension) - File is not empty
If the file has YAML frontmatter, note it — frontmatter must be preserved exactly.
Step 2: Mode Selection
If --lossless was passed in arguments, use lossless mode. Otherwise, use AskUserQuestion to ask:
- Lossy (recommended) — semantic compression with compressor-reviewer loop. Maximum token reduction.
- Lossless — structural optimization only. Zero semantic change.
If --auto was passed in arguments, enable auto-approve mode and skip the question below. Otherwise, immediately after the mode selection answer is received, use AskUserQuestion to ask about review style — do NOT proceed to Step 3 until this question is answered:
- Section-by-section (recommended) — review and approve/skip/edit each section individually.
- Auto-approve — compress all sections without per-section review. The
compression-revieweragent still runs in lossy mode and auto-incorporates fixes, but the user is not gated.
Both mode and review style must be resolved before moving to Step 3.
Step 3: Pre-Analysis
Read the full file and analyze its structure:
- Parse the heading hierarchy (identify all
#,##,###, etc.) - Split the file into sections at the highest sensible heading level (typically
##) - For each section, count approximate tokens (words * 1.3)
- Flag any structural issues:
- Skipped heading levels (e.g.,
#→###) - Sections over ~500 tokens (candidates for attention)
- Empty sections
- Duplicate content across sections
- Skipped heading levels (e.g.,
Present the structural analysis as a table:
| # | Section | Tokens | Notes |
|---|---------|--------|-------|
| 1 | Overview | ~130 | |
| 2 | Configuration | ~340 | |
| 3 | Deployment | ~520 | Large section |
| 4 | Testing | ~0 | Empty |
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 · 173 lines · 27 tokens per session scan A d3684c9efe75
compress is a command published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 27 tokens to every session and 1,649 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.