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 pomagrenate/ice_age --skill iceage-helpgit clone --depth 1 https://github.com/pomagrenate/ice_ageWrote 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-help)<a href="https://agentmods.dev/skills/pomagrenate/ice_age/iceage-help"><img src="https://agentmods.dev/badge/skills/pomagrenate/ice_age/iceage-help/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-help"><img src="https://agentmods.dev/badge/skills/pomagrenate/ice_age/iceage-help.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 | $0.00053 | $0.00524 |
| Opus 5.5 | $0.00021 | $0.00210 |
| Sonnet 5.5 | $0.00011 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
iceage-help 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
Iceage Help
Display this reference card when invoked. One-shot — do NOT change mode, write flag files, or persist anything. Output in iceage style.
Modes
| Mode | Trigger | What change |
|---|---|---|
| Lite | /iceage lite |
Drop filler. Keep sentence structure. |
| Full | /iceage |
Drop articles, filler, pleasantries, hedging. Fragments OK. Default. |
| Ultra | /iceage ultra |
Extreme compression. Bare fragments. Tables over prose. |
| Wenyan-Lite | /iceage wenyan-lite |
Classical Chinese style, light compression. |
| Wenyan-Full | /iceage wenyan |
Full 文言文. Maximum classical terseness. |
| Wenyan-Ultra | /iceage wenyan-ultra |
Extreme. Ancient scholar on a budget. |
Mode stick until changed or session end.
Skills
| Skill | Trigger | What it do |
|---|---|---|
| iceage-commit | /iceage-commit |
Terse commit messages. Conventional Commits. ≤50 char subject. |
| iceage-review | /iceage-review |
One-line PR comments: L42: bug: user null. Add guard. |
| iceage-compress | /iceage:compress <file> |
Compress .md files to iceage prose. Saves ~46% input tokens. |
| iceage-help | /iceage-help |
This card. |
Deactivate
Say "stop iceage" or "normal mode". Resume anytime with /iceage.
Configure Default Mode
Default mode = full. Change it:
Environment variable (highest priority):
export ICEAGE_DEFAULT_MODE=ultra
Config file (~/.config/iceage/config.json):
{ "defaultMode": "lite" }
Set "off" to disable auto-activation on session start. User can still activate manually with /iceage.
Resolution: env var > config file > full.
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 · 56 lines · 53 tokens per session scan A c44c7bf03331
iceage-help is a skill published in the GitHub repository pomagrenate/ice_age (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 524 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 2026-09-11.
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.
batch-small-questions-together
Group related short questions into one structured request while keeping each answer identifiable.
stellaris-explore
Route code exploration through Stellaris MCP: FTS for identifiers, hybrid for intent, outline/symbol for large files, host grep/rg for occurrences. Use when reconning a repo, finding a symbol, reading a large file, or when the user asks where something lives in the code.
contextcrumb
Compress large local files before adding them to LLM context. Use for docs, notes, transcripts, threads, logs, research dumps, and supported source files where only comments/docstrings should be compressed.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.