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 skills add DVNghiem/FlowDeck --skill context-steward-triggersgit 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-triggers)<a href="https://agentmods.dev/skills/dvnghiem/flowdeck/context-steward-triggers"><img src="https://agentmods.dev/badge/skills/dvnghiem/flowdeck/context-steward-triggers/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dvnghiem/flowdeck/context-steward-triggers"><img src="https://agentmods.dev/badge/skills/dvnghiem/flowdeck/context-steward-triggers.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00034 | $0.00321 |
| Opus 5 | $0.00017 | $0.00161 |
| Sonnet 5 | $0.00007 | $0.00064 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
context-steward-triggers 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 9d 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.
What it actually says
Context Health Triggers
Check context health after every stage transition and after every 3 task() calls.
Thresholds
| Context Usage | Action |
|---|---|
| > 40% | Run 3-pass prune (dedup → purge errors → compress stale) |
| > 60% | Compact + prune, then /fd-checkpoint |
| > 80% | /fd-checkpoint immediately before continuing |
Also trigger prune when:
- Multiple agents have contributed outputs in one session
- About to switch stages (fd-task → fd-review → fd-execute → fd-verify → fd-done)
- Any single tool output exceeds ~5000 tokens
Quick Actions
Prune (< 60%): Remove duplicate reads, resolved errors, stale turns. Keep session alive.
Compact (60–80%): Replace ranges with summaries + evidence links. Then checkpoint.
Checkpoint (> 80% or task complete): /fd-checkpoint → start fresh session.
Protected — Never Prune
AGENTS.md, STATE.md, active PLAN.md, DECISIONS.jsonl, FAILURES.json,
last 2 user messages, in-flight tool results.
Full Pipeline
Load the context-steward skill on demand when executing a prune.
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.
- 9d ago First seen · 39 lines · 34 tokens per session scan A 93c725ad6a86
context-steward-triggers is a skill published in the GitHub repository DVNghiem/FlowDeck (25 stars, last pushed 20d ago), licensed MIT. It adds 34 tokens to every session and 321 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
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.
simplify
Simplifies code for clarity without changing behavior. Use for readability, maintainability, and complexity reduction after behavior is understood.