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/context-stewardnpx skills add DVNghiem/FlowDeck --skill context-stewardgit clone --depth 1 https://github.com/DVNghiem/FlowDeckWrote 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/dvnghiem/flowdeck/context-steward)<a href="https://agentmods.dev/skills/dvnghiem/flowdeck/context-steward"><img src="https://agentmods.dev/badge/skills/dvnghiem/flowdeck/context-steward.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 | $0.00046 | $0.02756 |
| Opus 5 | $0.00023 | $0.01378 |
| Sonnet 5 | $0.00009 | $0.00551 |
| Haiku 4.5 | $0.00005 | $0.00276 |
Grade A, and why
context-steward 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 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.
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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Steward
FlowDeck sessions accumulate noise. Tool outputs, rule loads, failed attempts, and multi-agent chatter fill the context window. This skill defines a unified lifecycle to keep context lean, relevant, and recoverable.
When to Activate
Activate when:
- Context exceeds 50% of the window and response quality drops
- Multiple agents have contributed outputs in one session
- Tool results are large (logs, diffs, file reads)
- You are about to switch phases (plan → execute → verify)
- A
/fd-checkpointis imminent
Core Principles
- Context is a liability — every token not serving the current task is a distraction
- Prune with purpose — never drop what the agent needs to continue
- Protect the thread — user intent, active plans, and safety records are non-negotiable
- Telemetry is cheap — write stats before pruning so patterns are visible later
Unified Context Lifecycle
1. Ingest
Everything that enters the session window:
| Source | Typical Size | Risk Level |
|---|---|---|
| User prompts | Small | Low — never prune |
| Tool results (read, edit, bash) | Variable | High — can be huge |
| Skill loads | Medium | Medium — load once per session |
| Rule injections | Small-Medium | Medium — stage-gated already |
| Agent outputs | Medium | Medium — may contain plans or decisions |
| Memory queries | Small | Low |
fdx-graph results |
Small-Medium | Low |
Ingest discipline: Before any large output enters context, ask whether it is needed for the next 5 turns. If not, summarize or redirect to file.
2. Filter
FlowDeck already gates rules by stage. Extend this discipline to all context sources.
| Current Stage | Load | Defer / Skip |
|---|---|---|
discuss |
Behavioral rules, AGENTS.md |
Coding standards, testing rules |
plan |
Architecture rules, planning rules | Security rules, lint rules |
execute |
Coding standards, language patterns, security | Debug rules (until needed) |
verify |
Testing, security, linting rules | Planning rules |
fix-bug |
Debug, testing rules | Architecture rules |
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 · 299 lines · 46 tokens per session scan A f0962590c26e
context-steward is a skill published in the GitHub repository DVNghiem/FlowDeck (24 stars, last pushed 16d ago), licensed MIT. It adds 46 tokens to every session and 2,756 once invoked, about $0.0002 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
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.
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.
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.