context-steward-triggers

context-steward-triggers is a skill for Claude Code, Codex from DVNghiem/FlowDeck. It costs 34 tokens per session (321 once invoked), scanned A, original, MIT.

A set of thresholds and quick actions for managing an AI agent’s context, the conversation and tool information available to it. It recommends pruning, compacting, or checkpointing as context usage grows.

In plain words
What is it for?
Use it after stage changes, after several agent calls, or when tool output is large. It guides when to remove duplicates, summarize older information, or save a checkpoint before continuing in a fresh session.
Why use it?
It helps avoid running out of context or losing track of work in a long session. It also identifies files, recent messages, and unfinished tool results that should not be removed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it after stage changes, after several agent calls, or when tool output is large. It guides when to remove duplicates, summarize older information, or save a checkpoint before continuing in a fresh session.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dvnghiem/flowdeck/context-steward-triggers
Install

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.

Any agent
npx skills add DVNghiem/FlowDeck --skill context-steward-triggers
Clone the repo
git clone --depth 1 https://github.com/DVNghiem/FlowDeck

Made for: Claude Code, Codex.

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-steward-triggers

README.md
[![agentmods](https://agentmods.dev/badge/skills/dvnghiem/flowdeck/context-steward-triggers/github.svg)](https://agentmods.dev/skills/dvnghiem/flowdeck/context-steward-triggers)
Your own site
<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.

agentmods 80×15 button for context-steward-triggers

Your own site · 80×15
<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>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 321 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 $0.00034 $0.00321
Opus 5 $0.00017 $0.00161
Sonnet 5 $0.00007 $0.00064
Haiku 4.5 $0.00003 $0.00032

Measured 9d ago against content hash 93c725ad6a86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

src/skills/context-steward-triggers/SKILL.md · 39 lines

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.

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. 9d ago First seen · 39 lines · 34 tokens per session scan A 93c725ad6a86

Subscribe to this mod's changes

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.

Related

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.

alvinunreal/oh-my-opencode-slim · 61 tokens

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…

alvinunreal/oh-my-opencode-slim · 76 tokens

codemap

Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.

alvinunreal/oh-my-opencode-slim · 34 tokens

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.

alvinunreal/oh-my-opencode-slim · 34 tokens

worktrees

Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.

alvinunreal/oh-my-opencode-slim · 23 tokens

simplify

Simplifies code for clarity without changing behavior. Use for readability, maintainability, and complexity reduction after behavior is understood.

alvinunreal/oh-my-opencode-slim · 27 tokens