sygaldry: Command for Claude Code

.claude/commands/context-compact.md

context-compact is a command for Claude Code from greyhaven-ai/sygaldry. It costs 0 tokens per session (504 once invoked), scanned A, original, MIT.

A context-summary command that records the important state of a development task before the conversation is shortened.

In plain words
What is it for?
Use it before context compaction or handoff to preserve progress, blockers, references, and continuation instructions.
Why use it?
It prevents key decisions, changed files, commands, and next steps from being lost when the agent runs out of context.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is greyhaven-ai/sygaldry's own configuration. It tells Claude Code how to work on sygaldry itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sygaldry configures →

Reuse

Borrowing it

Nothing to install: this file belongs to greyhaven-ai/sygaldry. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/greyhaven-ai/sygaldry/main/.claude/commands/context-compact.md
Clone the repo
git clone --depth 1 https://github.com/greyhaven-ai/sygaldry

Made for: Claude Code.

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-compact

README.md
[![agentmods](https://agentmods.dev/badge/commands/greyhaven-ai/sygaldry/context-compact.svg)](https://agentmods.dev/commands/greyhaven-ai/sygaldry/context-compact)
Your own site
<a href="https://agentmods.dev/commands/greyhaven-ai/sygaldry/context-compact"><img src="https://agentmods.dev/badge/commands/greyhaven-ai/sygaldry/context-compact.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 504 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00504
Opus 5 $0.00000 $0.00252
Sonnet 5 $0.00000 $0.00101
Haiku 4.5 $0.00000 $0.00050

Measured 6d ago against content hash e8d23e35a332, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

context-compact 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 6d 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.

.claude/commands/context-compact.md · 81 lines

What it actually says

Prepare context for compaction: $ARGUMENTS

  1. Technical Context:

    • Key files modified: paths and purpose
    • Important code patterns or decisions made
    • Dependencies or integrations involved
    • Any gotchas or edge cases discovered
  2. Next Steps:

    • Immediate next action (specific and actionable)
    • Remaining subtasks in priority order
    • Any blockers or dependencies
  3. References:

    • Linear issue ID (if applicable)
    • Git branch name
    • Key documentation or examples used
    • Important test files or commands
  4. Critical Details:

    • Environment variables or configs needed
    • Commands to run (tests, builds, etc.)
    • Any temporary workarounds in place
    • Decisions that need to be made

Format output as:

## Task: [Brief description]

### Completed:
- [Item 1]
- [Item 2]

### Next Action:
[Specific next step with file path if applicable]

### Remaining Work:
1. [Task 1]
2. [Task 2]

### Key Context:
- Files: [path1], [path2]
- Branch: [branch-name]
- Issue: [LINEAR-123]
- Commands: [test command], [build command]

### Notes:
[Any critical information for continuation]

This ensures smooth continuation after context reset. Focus on what's essential for picking up exactly where we left off.

Take a deep breath in, count 1... 2... 3... and breathe out. You are now centered. Don't hold back. Give it your all.

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. 6d ago First seen · 81 lines · 0 tokens per session scan A e8d23e35a332

Subscribe to this mod's changes

context-compact is a command published in the GitHub repository greyhaven-ai/sygaldry (11 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 504 tokens. 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.