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 navendubrajesh/context-management-for-agents --skill context-compressiongit clone --depth 1 https://github.com/navendubrajesh/context-management-for-agentsWrote 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/navendubrajesh/context-management-for-agents/context-compression)<a href="https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/context-compression"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/context-compression/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/navendubrajesh/context-management-for-agents/context-compression"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/context-compression.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 | $0.00068 | $0.01468 |
| Opus 5 | $0.00034 | $0.00734 |
| Sonnet 5 | $0.00014 | $0.00294 |
| Haiku 4.5 | $0.00007 | $0.00147 |
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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Compression Strategies
Design compression strategies that preserve task-critical state while shedding accumulated noise. Compression is not lossless — every strategy trades fidelity for capacity. The engineering challenge is choosing what to lose, when to compress, and how to verify that compressed context retains sufficient signal for the task.
When to Activate
Activate this skill when:
- Long-running sessions accumulate history that approaches context limits
- Designing handoff summaries for agent-to-agent or session-to-session transitions
- Choosing between compression strategies (summarization, truncation, selective retention)
- Evaluating compression quality — what was preserved, what was lost
- Building systems that must maintain coherence across many turns
Do not activate this skill for adjacent work owned by other skills:
- Explaining why context degrades without an active compression task:
context-fundamentals. - Diagnosing specific failure patterns in degraded contexts:
context-degradation. - Applying tactical token-efficiency techniques (masking, caching, partitioning):
context-optimization. - Offloading content to filesystem rather than compressing it:
filesystem-context. - Workspace/git state handoff (branch, dirty files, resume commands): GStack
/context-saveand/context-restore— those save where you are, not what the conversation means.
Core Concepts
Compression operates on a fidelity-capacity trade-off curve. At one extreme, verbatim retention preserves all information but consumes maximum tokens. At the other extreme, aggressive summarization minimizes tokens but loses nuance, context, and recoverable detail. The optimal compression point depends on the task: creative tasks tolerate more information loss than debugging tasks.
Apply compression proactively, not reactively. By the time context is full, compression under pressure produces lower-quality summaries because the model's attention is already degraded. Set compression triggers at 60-70% of effective context capacity, leaving headroom for the compression operation itself and subsequent work.
What ships with it
1 file 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.
- 10d ago First seen · 133 lines · 68 tokens per session scan A 32d31b1d8e88
context-compression is a skill published in the GitHub repository navendubrajesh/context-management-for-agents (2 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 1,468 once invoked, about $0.0003 per session on Opus 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.