Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/pomagrenate/ice_agenpx agentmods add skills/pomagrenate/ice_age/iceage-batchWrote 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/pomagrenate/ice_age/iceage-batch)<a href="https://agentmods.dev/skills/pomagrenate/ice_age/iceage-batch"><img src="https://agentmods.dev/badge/skills/pomagrenate/ice_age/iceage-batch/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/pomagrenate/ice_age/iceage-batch"><img src="https://agentmods.dev/badge/skills/pomagrenate/ice_age/iceage-batch.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 | $0.00055 | $0.00422 |
| Opus 5.5 | $0.00022 | $0.00169 |
| Sonnet 5.5 | $0.00011 | $0.00084 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
iceage-batch 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
Compress all compressible files in a directory. Uses Claude API per file.
Usage
go run ./iceage-batch/go <directory> [flags]
Flags:
--dry-run— list files that would be compressed, no API calls--no-backup— skip creating.original.mdbackups (good for version-controlled dirs)--workers N— parallel compression (default 1, increase carefully — API rate limits apply)--recursive=false— top-level only, no subdirectories
Examples
go run ./iceage-batch/go docs/
go run ./iceage-batch/go docs/ --dry-run
go run ./iceage-batch/go docs/ --no-backup
go run ./iceage-batch/go docs/ --workers 3
go run ./iceage-batch/go . --recursive=false
Requirements
ANTHROPIC_API_KEY in environment or .env.local. Falls back to claude CLI if no key.
Output
Found 8 compressible file(s) in docs/
[1/8] docs/guide.md ... OK (1.2s)
[2/8] docs/api.md ... OK (0.9s)
[3/8] docs/old.md ... Skipped (backup exists)
[4/8] docs/broken.md ... FAILED (validation failed after retries)
Done
Compressed: 6
Skipped: 1
Failed: 1
Exit codes: 0 = all OK, 1 = fatal error, 2 = one or more files failed.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 54 lines · 55 tokens per session scan A 2842e47f8b67
iceage-batch is a skill published in the GitHub repository pomagrenate/ice_age (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 422 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 2026-08-31.
Other skills, from other repositories
token-saver
Reduce avoidable token and API cost through task-aware model selection, context hygiene, concise responses, and disciplined tool use. Apply as an advisory policy on every turn. Actual savings vary by agent, model, provider, cache behavior, and workload; measure results instead of assuming a fixed percentage.
code-to-diagram
Analyze codebases and automatically generate architecture diagrams, flowcharts, and org charts. Uses AST parsing to map import dependencies for Python, JS/TS, Go, and Java, outputting Mermaid or SVG files. Triggered when users ask to visualize code architecture, understand dependencies, draw a flowchart, or create a…
tree-sitter-language-pack-extracting-code-structure
Use when the user wants structured code metadata from a source file — functions, classes, imports, exports, symbols, docstrings, comments, or syntax diagnostics. Covers ts-pack process feature flags, the JSON result shape, and the default feature set.
tree-sitter-language-pack-chunking-for-llms
Use when the user wants to split source code into chunks for an LLM context window without breaking syntax mid-construct. Covers ts-pack process --chunk-size, why syntax-aware splits beat fixed-byte splits, picking a size, and the chunk JSON shape.
tree-sitter-language-pack-using-the-mcp-server
Use when parsing source, extracting code structure, or detecting a language through the tree-sitter-language-pack MCP server's tools, rather than shelling out to the ts-pack CLI. Covers the tool surface, the auto-installing launcher, and when MCP beats the CLI or SDK.
entroly-context-control
Surgically select, compress, and recover codebase context using Entroly's MCP tools. Slashes token usage by up to 95% with Merkle-exact recovery receipts and WITNESS verification.