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 filesystem-contextgit 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/filesystem-context)<a href="https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/filesystem-context"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/filesystem-context/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/filesystem-context"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/filesystem-context.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 | $0.00072 | $0.01314 |
| Opus 5 | $0.00036 | $0.00657 |
| Sonnet 5 | $0.00014 | $0.00263 |
| Haiku 4.5 | $0.00007 | $0.00131 |
Grade A, and why
filesystem-context 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Filesystem-Based Context Management
The filesystem provides a single interface for storing, retrieving, and updating effectively unlimited context outside the model's context window. Unlike in-context memory, filesystem storage has zero token cost until content is actively read, supports random access, persists across sessions, and is accessible by multiple agents simultaneously.
When to Activate
Activate this skill when:
- Offloading large tool outputs to avoid context bloat
- Persisting plans and progress across long-horizon tasks
- Enabling sub-agent communication via shared files
- Implementing just-in-time context loading from structured files
- Designing scratch pad patterns for working memory extension
- Building discovery mechanisms using standard file operations
Do not activate this skill for adjacent work owned by other skills:
- Designing memory architecture (vector RAG, knowledge graphs):
memory-systems. - Compressing conversation history into summaries:
context-compression. - Building hosted sandbox environments:
hosted-agents. - Diagnosing context degradation in loaded content:
context-degradation. - Storing QA artifacts or design outputs from workflow skills: prefer GStack artifact paths or project
.scratch/— this skill owns reference patterns, not release workflow storage.
Core Concepts
Use the filesystem as an attention-budget multiplier. Instead of loading entire documents into context, maintain lightweight references (file paths, content summaries) and load data just-in-time when the current task requires it. This mirrors human cognition: maintain an index, retrieve on demand.
Agents navigate filesystems effectively using four primitives: ls for structure discovery, glob for pattern matching, grep for content search, and read_file for targeted loading. These often outperform semantic search for structural queries because they provide deterministic, exact-match results.
Detailed Topics
Scratch Pad Pattern
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 · 146 lines · 72 tokens per session scan A 48a1c58c3243
filesystem-context is a skill published in the GitHub repository navendubrajesh/context-management-for-agents (2 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 1,314 once invoked, about $0.0004 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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.