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 agentmods add skills/docxology/template/context-compressionnpx skills add docxology/template --skill context-compressiongit clone --depth 1 https://github.com/docxology/templateWhat 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 | $0.00047 | $0.03438 |
| Opus 5 | $0.00023 | $0.01719 |
| Sonnet 5 | $0.00009 | $0.00688 |
| Haiku 4.5 | $0.00005 | $0.00344 |
Grade A, and why
context-compression 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 2d 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.
This is a copy
100% identical to context-compression — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Compression Strategies
When agent sessions generate millions of tokens of conversation history, compression becomes mandatory. The naive approach is aggressive compression to minimize tokens per request. The correct optimization target is tokens per task: total tokens consumed to complete a task, including re-fetching costs when compression loses critical information.
When to Activate
Activate this skill when:
- Agent sessions exceed context window limits
- Codebases exceed context windows (5M+ token systems)
- Designing conversation summarization strategies
- Debugging cases where agents "forget" what files they modified
- Building evaluation frameworks for compression quality
- Creating durable handoff summaries that preserve decisions, files, risks, and next actions
Do not activate this skill for adjacent work owned by other skills:
- General token-efficiency tactics such as masking, prefix caching, or partitioning:
context-optimization. - Diagnosing why a long context is failing before choosing a mitigation:
context-degradation. - Writing raw outputs, logs, or plans to files without summarizing them:
filesystem-context. - Designing long-term semantic memory across sessions:
memory-systems.
Core Concepts
Context compression trades token savings against information loss. Select from three production-ready approaches based on session characteristics:
- Anchored Iterative Summarization: Implement this for long-running sessions where file tracking matters. Maintain structured, persistent summaries with explicit sections for session intent, file modifications, decisions, and next steps. When compression triggers, summarize only the newly-truncated span and merge with the existing summary rather than regenerating from scratch. This prevents drift that accumulates when summaries are regenerated wholesale — each regeneration risks losing details the model considers low-priority but the task requires. Structure forces preservation because dedicated sections act as checklists the summarizer must populate, catching silent information loss.
What ships with it
3 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.
- 2d ago First seen · 280 lines · 47 tokens per session scan A c4111db0514e
context-compression is a skill published in the GitHub repository docxology/template (19 stars, last pushed 2d ago), licensed Apache-2.0. It adds 47 tokens to every session and 3,438 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to context-compression, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
planning-with-files
Manus-style persistent file-based planning for AI coding agents: keeps taskplan.md, findings.md, and progress.md on disk so work survives context loss and /clear. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+ tool calls. Supports automatic session…
exa-search
Use Exa MCP for current web, code/docs, company, people, and page-fetch research. Prefer current hosted tool schemas and note deprecated tools.
ontoly-software-graph
Use Ontoly's deterministic Software Graph and MCP capabilities for repository architecture, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to source search.
product-decision-agent
中文产品决策 Agent。用于中国大陆互联网产品、运营、增长、商业化、数据、项目推进和组织协作场景：产品规划、需求分析、PRD、需求优先级、排期、版本规划、Roadmap、MVP、灰度、上线、迭代、增长停滞、拉新、投放、渠道、裂变、CAC、LTV、ROI、留存、转化、DAU/MAU、GMV、漏斗、社区运营、内容供给、创作者、用户运营、活动运营、私域、会员、定价、指标异常、数据口径、埋点、A/B…
kimi-webbridge
Kimi WebBridge lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login sessions. Use this skill whenever the user wants to interact with websites, automate browser tasks, scrape web content, or perform any action requiring a real…
acupuncturist
Use when a task needs the judgment of a licensed acupuncturist — building a TCM pattern-differentiation-based treatment plan, choosing point combinations and needling technique for a presenting complaint, triaging a safety red flag (fainting, suspected pneumothorax, herb-drug interaction), or writing a SOAP note that…