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 ZachBeta/claude-as-coach --skill context-curation-basegit clone --depth 1 https://github.com/ZachBeta/claude-as-coachWrote 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/zachbeta/claude-as-coach/context-curation-base)<a href="https://agentmods.dev/skills/zachbeta/claude-as-coach/context-curation-base"><img src="https://agentmods.dev/badge/skills/zachbeta/claude-as-coach/context-curation-base/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/skills/zachbeta/claude-as-coach/context-curation-base"><img src="https://agentmods.dev/badge/skills/zachbeta/claude-as-coach/context-curation-base.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 | $0.00074 | $0.02508 |
| Opus 5 | $0.00037 | $0.01254 |
| Sonnet 5 | $0.00015 | $0.00502 |
| Haiku 4.5 | $0.00007 | $0.00251 |
Grade A, and why
context-curation-base 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 9d 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Curation Skill
Created: Monday, January 19, 2026 Updated: Monday, January 20, 2026 Purpose: Systematic process for managing project file context after retros/planning sessions Status: Experimental
Overview
Context curation follows the "fractal compression" pattern: each level of summary makes the previous level's raw inputs archivable. Before archiving, fold extractable data into addendums or reference docs.
Trigger phrases:
- "context curation"
- "clean up project files"
- "archive old summaries"
- "what can we remove"
Compression Hierarchy
Daily summaries → Weekly retros → Monthly retros → Quarterly retros → Yearly retros
| After completing... | These can be archived... |
|---|---|
| Daily summary | Raw conversation logs for that day |
| Weekly retro | Daily summaries for that week |
| Monthly retro | Weekly retros for that month |
| Quarterly retro | Monthly retros for that quarter |
| Yearly retro | Quarterly retros for that year |
Principle: Keep at least one copy at each granularity level.
Retention Minimums
Keep at least one document at each granularity level:
| Level | Minimum to Keep |
|---|---|
| Daily | 1-2 most recent summaries |
| Weekly | Current week's plan + most recent retro |
| Monthly | Current month's plan + most recent retro |
| Quarterly | Current quarter's plan + most recent retro |
| Yearly | Current year's plan + most recent retro |
Principle: Even after compression, maintain the ability to see recent state at each time scale.
Fold Before Archive
Before archiving daily summaries, extract data that should persist in reference docs.
What to Extract
- Quantitative progress (reps, times, measurements, PRs)
- Protocol changes or discoveries
- Status updates for tracked items
- Confirmed additions (new safe foods, new movements, etc.)
Where to Extract
Addendum files for reference docs that accumulate data:
Reference-Doc.md→Reference-Doc-Addendum-YYYY-MM-DD-to-DD.md- Date range matches the weekly retro period
- Example:
Training-Log-Addendum-2026-02-16-to-22.md
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.
- 9d ago First seen · 330 lines · 74 tokens per session scan A 69cb045b02f2
context-curation-base is a skill published in the GitHub repository ZachBeta/claude-as-coach (5 stars, last pushed 7mo ago), licensed MIT. It adds 74 tokens to every session and 2,508 once invoked, about $0.0004 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.