OpenAgents Control is a framework that adds plan-first, approval-based coding workflows to OpenCode, an AI coding framework. Developers and teams use it to make agents follow shared coding patterns, work across several programming languages, and validate changes through testing and review. The catalogue includes its agents, skills, commands, plugin, and hook.
Borrowing it
Nothing to install: this file belongs to darrenhinde/OpenAgentsControl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/darrenhinde/OpenAgentsControl/main/.opencode/skills/context-manager/SKILL.mdgit clone --depth 1 https://github.com/darrenhinde/OpenAgentsControlWrote 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/darrenhinde/openagentscontrol/context-manager)<a href="https://agentmods.dev/skills/darrenhinde/openagentscontrol/context-manager"><img src="https://agentmods.dev/badge/skills/darrenhinde/openagentscontrol/context-manager/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/darrenhinde/openagentscontrol/context-manager"><img src="https://agentmods.dev/badge/skills/darrenhinde/openagentscontrol/context-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 28 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- high Data Exfiltration · line 164 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 | $0.00027 | $0.02979 |
| Opus 5.5 | $0.00011 | $0.01192 |
| Sonnet 5.5 | $0.00005 | $0.00596 |
| Haiku 4.5 | $0.00003 | $0.00298 |
Grade A, and why
context-manager 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.
How it starts
The opening of the file, as written. The whole thing — 569 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Manager Skill
Purpose: Comprehensive context management operations with clear guidance, lazy loading, and safe operations for discovering, organizing, and maintaining project context.
What I Do
I provide 8 powerful operations for managing context:
- DISCOVER - Find context files by topic or path
- FETCH - Get external documentation from libraries
- HARVEST - Extract context from summary files
- EXTRACT - Pull specific information from context
- COMPRESS - Reduce large file sizes
- ORGANIZE - Restructure context by concern
- CLEANUP - Remove stale or temporary files
- PROCESS - Guided workflow for context operations
Quick Start
1. Discover Context
bash .opencode/skills/context-manager/router.sh discover authentication
Finds all context files related to authentication patterns.
2. Fetch External Documentation
bash .opencode/skills/context-manager/router.sh fetch "Drizzle ORM" "modular schemas"
Retrieves live documentation from external libraries.
3. Harvest Context
bash .opencode/skills/context-manager/router.sh harvest ANALYSIS.md
Extracts key concepts from summary files into permanent context.
4. Extract Information
bash .opencode/skills/context-manager/router.sh extract code-quality.md "naming conventions"
Pulls specific information from context files.
5. Compress Files
bash .opencode/skills/context-manager/router.sh compress .opencode/context/ 100KB
Reduces large context files to save space.
6. Organize Context
bash .opencode/skills/context-manager/router.sh organize .opencode/context/
Restructures context by concern for better organization.
7. Cleanup Stale Files
bash .opencode/skills/context-manager/router.sh cleanup .tmp/ 7
Removes temporary or old files (older than 7 days).
8. Guided Workflow
bash .opencode/skills/context-manager/router.sh process "organize authentication context" .opencode/context/
Step-by-step guidance for complex context operations.
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.
- 1mo ago First seen · 569 lines · 27 tokens per session scan A 1c2a055c8a7f
context-manager is a skill published in the GitHub repository darrenhinde/OpenAgentsControl (4,925 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 2,979 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
cortivex-context-compression
Compress agent outputs for efficient context handoff between pipeline nodes while preserving actionable information.
llm-integration
Claude and OpenAI API patterns, prompt design, context management, streaming, tool use, cost control, multi-model routing.
knowledge-base
Create and maintain a Markdown knowledge base that any AI agent can read, search, and update. Use when the user wants to start a knowledge base, add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers…
obsidian-vault
Organize Obsidian vaults with MOCs, wikilinks, frontmatter/properties, dashboards, orphan-note checks, and cleanup workflows. Use ONLY when the user explicitly refers to Obsidian — by naming "Obsidian", an Obsidian "vault", or an Obsidian-specific feature such as wikilinks ("[[ ]]"), the Dataview or Bases plugins, or…
project-wiki
A system for creating and maintaining a project wiki: a set of organized documents that explain a software project's plans, rules, references, and progress.
mindos-zh
A local knowledge-base assistant for storing and finding decisions, meeting notes, procedures, troubleshooting lessons, and preferences across conversations and coding agents. It works only with the MindOS knowledge base.