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 juyterman1000/entroly --skill entroly-context-controlgit clone --depth 1 https://github.com/juyterman1000/entrolyWrote 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/juyterman1000/entroly/entroly-context-control)<a href="https://agentmods.dev/skills/juyterman1000/entroly/entroly-context-control"><img src="https://agentmods.dev/badge/skills/juyterman1000/entroly/entroly-context-control/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/juyterman1000/entroly/entroly-context-control"><img src="https://agentmods.dev/badge/skills/juyterman1000/entroly/entroly-context-control.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 | $0.00048 | $0.00445 |
| Opus 5.5 | $0.00019 | $0.00178 |
| Sonnet 5.5 | $0.00010 | $0.00089 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
entroly-context-control 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.
What it actually says
Entroly Context Intelligence Skill
Use this skill to optimize context, query the codebase with token budgets, compress bulky tool outputs, and recover omitted code byte-for-byte using the Entroly MCP server.
Core Workflows
1. Token-Budgeted Codebase Selection (optimize_context)
When answering a complex question or preparing a refactor across multiple files:
- Call
optimize_contextwith your natural language query and a token budget (e.g.,budget=4000orbudget=8000). - Entroly executes a knapsack optimization algorithm that ranks AST fragments by relevance, entropy, and dependency relations.
- Returns surgical code fragments, line numbers, and a cryptographic Merkle receipt.
2. Semantic Code Recall (recall)
When searching for specific symbols, implementations, or interfaces:
- Call
recall(query="...")withtop_k=5ortop_k=10. - Returns ranked pointers with filenames, line numbers, and snippet digests.
3. Reversible Output Compression (compress & recover)
When dealing with large terminal dumps (build traces, test logs):
- Call
compress(data=..., budget=...)to distill down critical errors and signals while stripping noise. - Every compression produces a content-addressed SHA-256 handle.
- To restore the original uncompressed text at any time, call
recover(handle="...").
4. Codebase Health & Architecture Diagnostics (health)
To assess codebase quality before or after major changes:
- Call
health()to inspect clone pairs, dead symbols, god files, and architecture violations.
5. Grounding & Hallucination Verification (witness_verify)
To verify an agent claim or proposed code against source evidence:
- Call
witness_verify(claim=..., evidence=...)for local NLI-backed verification.
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 · 36 lines · 48 tokens per session scan A 497ad46e216b
entroly-context-control is a skill published in the GitHub repository juyterman1000/entroly (476 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 445 once invoked, about $0.0002 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 2026-09-15.
Other skills, from other repositories
thread
Manage persistent context threads for cross-session work.
lean-ctx
Pick the right lean-ctx tool for reading, searching, understanding and running code with fewer tokens and fewer round trips. Use when lean-ctx MCP tools (ctx) are available or when a command output, file read or search would be large.
lean-ctx
Pick the right lean-ctx tool for reading, searching, understanding and running code with fewer tokens and fewer round trips. Use when lean-ctx MCP tools (ctx) are available or when a command output, file read or search would be large.
dream-memory
Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md short enough for prompt use.
memory-extractor
Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts.
structured-context-compressor
Compress a long agent conversation into a nine-part continuation summary that preserves request, files, errors, user messages, current work, and the next aligned step.