context-guard

context-guard is a skill for Claude Code, Codex from DVNghiem/FlowDeck. It costs 28 tokens per session (1,418 once invoked), scanned A, original, MIT.

A rule set for protecting important conversation and project information when an AI agent compacts its context, meaning it shortens older conversation history to make room for more work. It protects plans, safety files, unfinished tool results, decisions, and the user’s goal.

In plain words
What is it for?
Use it to define files, tool calls, decisions, and messages that must survive context pruning. Its default registry can be overridden in .opencode/flowdeck/protected-patterns.yaml.
Why use it?
It helps prevent the agent from forgetting essential instructions or current work during a long task. Without these protections, the agent may lose decisions or repeat work after context is shortened.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/dvnghiem/flowdeck/context-guard
Any agent
npx skills add DVNghiem/FlowDeck --skill context-guard
Clone the repo
git clone --depth 1 https://github.com/DVNghiem/FlowDeck

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for context-guard

README.md
[![agentmods](https://agentmods.dev/badge/skills/dvnghiem/flowdeck/context-guard.svg)](https://agentmods.dev/skills/dvnghiem/flowdeck/context-guard)
Your own site
<a href="https://agentmods.dev/skills/dvnghiem/flowdeck/context-guard"><img src="https://agentmods.dev/badge/skills/dvnghiem/flowdeck/context-guard.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,418 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.01418
Opus 5 $0.00014 $0.00709
Sonnet 5 $0.00006 $0.00284
Haiku 4.5 $0.00003 $0.00142

Measured 4d ago against content hash 42edd00fe630, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-guard 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 4d 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.

src/skills/context-guard/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Guard Skill

Defines the protected-pattern contract: a whitelist of files, tools, decisions, and messages that must survive context compaction.

What Is a Protected Pattern?

A protected pattern is any context item that a pruning pass must skip. Without it, compaction can silently discard the very state an agent needs to finish a task.

Four categories:

Tool Patterns

Tool invocations that must remain in the conversation window while they are in flight or unverified. Example: a write or edit call whose result has not yet been confirmed.

File Patterns

Paths that anchor the current session. These include active planning files, project conventions, and safety ledgers.

Decision Records

Records that explain why the session is in its current state. Removing them forces the agent to re-derive intent from scratch.

Intent Anchors

User messages that establish the original goal and the most recent steering corrections. These are the cheapest way to prevent drift.

Default Protected-Pattern Registry

FlowDeck ships with a default registry. Override it in .opencode/flowdeck/protected-patterns.yaml, never by editing this skill.

System Files

Pattern Reason
AGENTS.md Operating rules for every agent
~/.fd-plan/<slug>/STATE.md Current phase, completed steps, blockers
~/.fd-plan/<slug>/<topic>/plan.md Active plan and success criteria

Safety Files

Pattern Reason
~/.fd-plan/<slug>/.codebase/DECISIONS.jsonl Decision ledger — why choices were made
~/.fd-plan/<slug>/.codebase/FAILURES.json Failure replay engine data

Intent Anchors

Pattern Reason
Last 2 user messages Original goal + latest steering
Current phase objective From STATE.md — the single sentence that defines success

Active Operations

Any pending tool whose side effects have not been verified:

Tool Condition
write while pending verification
edit while pending verification
bash while exit code/output not yet checked

Read the full file on GitHub · 173 lines

Changes

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.

  1. 4d ago First seen · 173 lines · 28 tokens per session scan A 42edd00fe630

Subscribe to this mod's changes

context-guard is a skill published in the GitHub repository DVNghiem/FlowDeck (24 stars, last pushed 15d ago), licensed MIT. It adds 28 tokens to every session and 1,418 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

crewai-multi-agent

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…

davila7/claude-code-templates · 61 tokens

oh-my-opencode-slim

Configure and improve oh-my-opencode-slim for the current user. Use when users want to tune agents, models, prompts, custom agents, skills, MCPs, presets, or plugin behavior. Also use when recurring workflow friction suggests a safe config or prompt improvement.

alvinunreal/oh-my-opencode-slim · 61 tokens

reflect

Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.

alvinunreal/oh-my-opencode-slim · 53 tokens

clonedeps

Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals. Use when the user asks to clone dependencies, inspect dependency/source internals, understand SDK/framework behavior from source, debug library implementation details, or make core dependency repos…

alvinunreal/oh-my-opencode-slim · 76 tokens

codemap

Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.

alvinunreal/oh-my-opencode-slim · 34 tokens

deepwork

High-cost orchestrator workflow for large, high-risk, multi-phase coding efforts with meaningful dependencies and review gates. Do not activate for routine multi-file changes.

alvinunreal/oh-my-opencode-slim · 34 tokens