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 agentmods add commands/ariegoldkin/claude-forge/setup-continuitygit clone --depth 1 https://github.com/ArieGoldkin/claude-forgeWrote 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/commands/ariegoldkin/claude-forge/setup-continuity)<a href="https://agentmods.dev/commands/ariegoldkin/claude-forge/setup-continuity"><img src="https://agentmods.dev/badge/commands/ariegoldkin/claude-forge/setup-continuity.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.01754 |
| Opus 5 | $0.00010 | $0.00877 |
| Sonnet 5 | $0.00004 | $0.00351 |
| Haiku 4.5 | $0.00002 | $0.00175 |
Grade B, and why
setup-continuity scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
if ! grep -q "\.claude/continuity/" .gitignore 2>/dev/null; then How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/setup-continuity - Initialize Continuity System
One-time setup wizard to ensure all continuity system components are properly configured.
When to Use
- First time setting up continuity system in a project
- After cloning a repo with existing continuity files
- When hooks or automation aren't working
- To verify system health after updates
What This Command Does
- Verify directories - Create missing continuity directories
- Update .gitignore - Ensure session state files are not committed
- Check settings.local.json - Ensure hooks are configured
- Initialize ledger - Create from template if missing
- Verify hook scripts - Check they're executable
- Initialize shared-context.json - Set up tracking fields
- Create initial handoff - Optional first checkpoint
Execution Steps
Step 1: Check Directory Structure
Verify and create required directories:
Required directories:
- .claude/
- .claude/commands/
- .claude/context/
- .claude/continuity/
- .claude/continuity/handoffs/
- .claude/continuity/ledgers/
- .claude/continuity/archive/
- .claude/continuity/learnings/
For any missing directories, create them:
mkdir -p .claude/continuity/{handoffs,ledgers,archive,learnings}
mkdir -p .claude/context
Step 2: Update .gitignore
Continuity files are user-specific session state and should NOT be committed to git. They contain:
- Personal working notes and timestamps
- Session-specific context that varies per developer
- Transient data that would cause merge conflicts
Check if .gitignore exists and contains the required entries:
# Claude session state (user-specific, not shared)
.claude/context/
.claude/continuity/
Implementation:
- Check if
.gitignoreexists in project root - If it exists, check if it already contains
.claude/continuity/ - If entries are missing, append them:
# Check and append if needed
if ! grep -q "\.claude/continuity/" .gitignore 2>/dev/null; then
echo "" >> .gitignore
echo "# Claude session state (user-specific, not shared)" >> .gitignore
echo ".claude/context/" >> .gitignore
echo ".claude/continuity/" >> .gitignore
fi
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.
- 5d ago First seen · 263 lines · 19 tokens per session scan B 7cbf6aa7cc3b
setup-continuity is a command published in the GitHub repository ArieGoldkin/claude-forge (6 stars, last pushed 27d ago), licensed MIT. It adds 19 tokens to every session and 1,754 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
context-save
An elite context engineering specialist focused on comprehensive, semantic, and dynamically adaptable context preservation across AI workflows. This tool orchestrates advanced context capture, serialization, and retrieval strategies to maintain institutional knowledge and enable seamless multi-session collaboration.
memory
Unified read-side memory operations including knowledge graph search, session context loading, decision timeline viewing, and Mermaid graph visualization. Subcommands: search, load, history, viz, status. Complements /ork:remember (write-side). Use when searching past decisions, loading context, or visualizing the…
compact-prep
Ask the agent to prepare for conversation compaction by updating any relevant state and providing guidance for the compaction agent and to kick off the session there after.
memory-review
Display current memory state with timestamps, sizes, and staleness indicators.
index
Create persistent project understanding via PROJECTMAP.md.
enrich
Enrich project memory by mining 100 recently merged PRs: extracts decisions, conventions, gotchas, and architectural facts from PR discussions, review comments, and PR bodies.