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 skills/dvnghiem/flowdeck/session-persistencenpx skills add DVNghiem/FlowDeck --skill session-persistencegit clone --depth 1 https://github.com/DVNghiem/FlowDeckWhat 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 | $0.00029 | $0.02770 |
| Opus 5 | $0.00015 | $0.01385 |
| Sonnet 5 | $0.00006 | $0.00554 |
| Haiku 4.5 | $0.00003 | $0.00277 |
Grade A, and why
session-persistence 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 2d 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Persistence
FlowDeck sessions are bounded by context windows. This skill ensures work survives across sessions without losing state, decisions, or momentum.
When to Activate
Activate at:
- Session start — before any agent does work
- Mid-session — when context exceeds 60% of the window
- Session end — before closing the workspace
Core Principles
- Load before you act. Never start work without reading the prior session summary.
- Checkpoint early and often. Ephemeral state is lost when the context window rolls over.
- Summaries are append-only. Each session adds a new entry; old entries rotate monthly.
- STATE.md owns the plan. SESSION_SUMMARY.md owns the narrative. Do not duplicate.
Phase 1: Session Start
Goal: Bring the agent up to speed on what happened in the previous session and what remains.
Files to Read
| File | Purpose | Max Chars | Required |
|---|---|---|---|
~/.fd-plan/<slug>/STATE.md |
Current phase, active plan, blockers, steps completed | 10,000 | Yes |
~/.fd-plan/<slug>/SESSION_SUMMARY.md |
Prior session narratives, decisions, failures, remaining work | 15,000 | Yes |
~/.fd-plan/<slug>/<topic>/plan.md |
Active plan with tasks and success criteria | 8,000 | If referenced in STATE.md |
~/.fd-plan/<slug>/.codebase/DECISIONS.jsonl |
Recent decisions relevant to active work | 5,000 | Query last 10 entries |
Information to Capture
- Phase and status — from STATE.md
- Last completed step — what was finished
- Next pending step — what should happen now
- Blockers — anything preventing progress
- Approaches that failed — avoid repeating them
- Key decisions — links to DECISIONS.jsonl entries
- Files modified — what changed recently
- Test status — green, failing, or unknown
Commands to Use
/fd-resume # Load STATE.md and latest SESSION_SUMMARY.md entry
/fd-status # Show current phase, next step, and blocker summary
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.
- 2d ago First seen · 321 lines · 29 tokens per session scan A e4c585d971f0
session-persistence is a skill published in the GitHub repository DVNghiem/FlowDeck (24 stars, last pushed 14d ago), licensed MIT. It adds 29 tokens to every session and 2,770 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.
Other skills, from other repositories
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.
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.
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…
codemap
Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.
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.
worktrees
Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.