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 skills add DojoGenesis/mcp --skill compression-ritualgit clone --depth 1 https://github.com/DojoGenesis/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/skills/dojogenesis/mcp/compression-ritual)<a href="https://agentmods.dev/skills/dojogenesis/mcp/compression-ritual"><img src="https://agentmods.dev/badge/skills/dojogenesis/mcp/compression-ritual.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.02086 |
| Opus 5 | $0.00035 | $0.01043 |
| Sonnet 5 | $0.00014 | $0.00417 |
| Haiku 4.5 | $0.00007 | $0.00209 |
Grade A, and why
compression-ritual 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 7d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compression Ritual
I. Philosophy: The Art of Letting Go
Compression is not destruction -- it is transformation. We transform the raw material of conversation into refined artifacts of wisdom. The goal is to lose volume while preserving meaning. Every token in a context window has a cost; compression ensures that cost buys wisdom, not noise.
The ritual framing matters. This is not "cleanup" or "archiving" -- it's a conscious, creative act of choosing what deserves to grow and what can be respectfully composted. The Art of Letting Go is the recognition that not everything deserves permanent cultivation, and that releasing context is an act of respect for future clarity.
Distillation follows a principle: compress the experience, not just the text. A good compression captures the meaning of a 3-hour session in 200 words, not just the first paragraph of each exchange.
II. When to Use This Skill
- After a long conversation (20+ turns or 30+ minutes)
- At the end of a major work session or sprint
- When the context window feels heavy or noisy -- too much raw material
- Before handing off a project to another agent or team member
- As a regular practice (end of day) to maintain cognitive hygiene
- When Tier A daily notes are piling up and need compression
When NOT to use: For short conversations with 1-2 key points, a simple daily note via /tend is sufficient. Don't ritualize what doesn't need it.
III. The Six-Step Compression Workflow
Step 1: Signal Intent
Announce the ritual to frame it as deliberate practice:
"We're entering a compression ritual. The goal is to distill this session into its essential wisdom."
Why this matters: Signaling shifts the mindset from "working" to "reflecting." It creates a boundary between the session and its compression.
Step 2: Review the Transcript
Read through the material looking for five types of significant moments:
- Key Decisions -- Choices that altered direction
- Profound Insights -- New understandings or "aha!" moments
- Actionable Learnings -- Lessons that inform future behavior
- Reusable Patterns -- Ideas generalizable into seeds
- Unresolved Questions -- Important items still open
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.
- 7d ago First seen · 207 lines · 70 tokens per session scan A 13b67fdefc5e
compression-ritual is a skill published in the GitHub repository DojoGenesis/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 2,086 once invoked, about $0.0003 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 skills, from other repositories
memory-index
Index a folder's contents into the MemPalace semantic memory for search and retrieval. Use this skill whenever the user asks to "index a folder", "index a directory", "index memory", "mine a project into memory", "make a folder searchable", "embed a folder", "ingest code into the palace", or "index this directory for…
memory-mine
Mine project files or conversations into the MemPalace memory system. Indexes source code and conversation history as searchable palace drawers with semantic embeddings and room assignment.
memory-status
Show MemPalace memory system status — drawer counts, wings, rooms, knowledge graph stats, and embedding model state.
notebrain-assistant
Search and explore an Obsidian vault through the NoteBrain CLI (semantic search, tags, backlinks, connections, hidden links, boosted retrieval). Use it whenever the user mentions their notes, knowledge base, Obsidian vault, semantic search, finding connections or unlinked notes, or asks exploratory questions like…
cartographer-ops
Configure, operate, troubleshoot, or upgrade a Cartographer server or client; connect agents and manage Knowledge Bases.
fkf-learn
Stage verified fkf findings as reviewable wiki or project diffs. Use after a durable decision, pattern, status change, dead end, or skill lesson.