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 Zfinix/aster --skill context-economygit clone --depth 1 https://github.com/Zfinix/asterWrote 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/zfinix/aster/context-economy)<a href="https://agentmods.dev/skills/zfinix/aster/context-economy"><img src="https://agentmods.dev/badge/skills/zfinix/aster/context-economy.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.00370 |
| Opus 5 | $0.00000 | $0.00185 |
| Sonnet 5 | $0.00000 | $0.00074 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
context-economy 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 8d 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
Context economy
- Big outputs go to files, then get queried.
git diff main > /tmp/change.diffthengrep -n "fn " /tmp/change.diff;gh pr diff 12 > /tmp/pr12.diff; a build log to/tmp/build.logthengrep -m5 error /tmp/build.log. Never print thousands of lines to look at twenty. - Summaries before bodies.
git diff --statbefore any full diff,wc -lbefore a full read,ls -labefore catting files. Decide what to open from the summary. - Delegate bulk reading. Reading ten files to answer one question fills
the conversation with nine files of noise. Send the question to the
exploreragent and get back only the conclusion. - Ranged reads, always. You almost never need a whole file: read the function, not the module. Ask for the specific line range the search hit pointed at.
- Do not re-read or re-run what is above. A file read earlier and unchanged is still in the conversation; an identical command gives an identical answer. Scroll back instead.
- Minimal-output probes for external checks. Checking that a URL exists needs a status code, not the page. Checking a fact in a doc needs one grep, not the document.
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.
- 8d ago First seen · 28 lines · 0 tokens per session scan A eeee4afaa621
context-economy is a skill published in the GitHub repository Zfinix/aster (57 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 370 tokens. 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 2026-08-30.
Other skills, from other repositories
speccrew-knowledge-bizs-dispatch
Dispatch bizs knowledge base generation tasks with 5-stage pipeline (XML Block version). Handles feature inventory, feature analysis with skill routing, graph data writing, module summarization, UI style pattern extraction, and system summary.
speccrew-knowledge-bizs-identify-entries
Analyze source directory structures to identify business module entry directories for each platform using XML workflow blocks. Use when initializing or updating business knowledge base to determine which directories contain user-facing entry points.
speccrew-knowledge-bizs-ui-graph
Constructs knowledge graph data (nodes, edges, relationships) from UI analysis results using XML workflow blocks. Generates graph JSON files and completion markers for the bizs knowledge pipeline.
speccrew-knowledge-graph-write
Write, update, and initialize knowledge graph data (nodes, edges, index, metadata). Used by Dispatch Agent after receiving graphData from analysis skills. Handles batch writes, deduplication, index updates, and module initialization.
speccrew-knowledge-techs-generate
Stage 2 of technology knowledge initialization - Generate technology documentation for a specific platform using XML workflow blocks. Extracts tech stack, architecture, and conventions from configuration files and source code. Creates INDEX.md, tech-stack.md, architecture.md, and conventions-.md files. Used by Worker…
speccrew-knowledge-techs-index
Stage 3 of technology knowledge initialization - Generate root INDEX.md by aggregating all platform technology documents using XML workflow blocks. Creates the master index that maps platforms to their documentation and provides Agent-to-Platform mapping guide. Used by Worker Agent after all platform documents are…