Claude Statusbar
leeguooooo/claude-code-usage-bar
Manage cs (claude-statusbar) — switch theme/style/density, override severity colors, preview combinations, run doctor, reset config, install, upgrade (cs upgrade — the only supported upgrade path)…
Context window monitoring and budget management. An agent skill from a5c-ai/babysitter.
Install Context Engineering
$ npx skills add a5c-ai/babysitter --skill context-engineering -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install a5c-ai/babysitter context-engineering --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/a5c-ai/babysitter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/library/methodologies/gsd/skills/context-engineering .claude/skills/context-engineering && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "context-engineering" agent skill from https://github.com/a5c-ai/babysitter/tree/main/library/methodologies/gsd/skills/context-engineering into .claude/skills/context-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/a5c-ai/babysitter/tree/main/library/methodologies/gsd/skills/context-engineeringType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add a5c-ai/babysitter --skill context-engineering -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install a5c-ai/babysitter context-engineering --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/a5c-ai/babysitter.git skills-src && mkdir -p .agents/skills && cp -r skills-src/library/methodologies/gsd/skills/context-engineering .agents/skills/context-engineering && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "context-engineering" agent skill from https://github.com/a5c-ai/babysitter/tree/main/library/methodologies/gsd/skills/context-engineering into .agents/skills/context-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add a5c-ai/babysitter --skill context-engineering -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install a5c-ai/babysitter context-engineering --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/a5c-ai/babysitter.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/library/methodologies/gsd/skills/context-engineering .cursor/skills/context-engineering && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "context-engineering" agent skill from https://github.com/a5c-ai/babysitter/tree/main/library/methodologies/gsd/skills/context-engineering into .cursor/skills/context-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/a5c-ai/babysitter.git --path library/methodologies/gsd/skills/context-engineering--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add a5c-ai/babysitter --skill context-engineering -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install a5c-ai/babysitter context-engineering --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/a5c-ai/babysitter.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/library/methodologies/gsd/skills/context-engineering .gemini/skills/context-engineering && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "context-engineering" agent skill from https://github.com/a5c-ai/babysitter/tree/main/library/methodologies/gsd/skills/context-engineering into .gemini/skills/context-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install a5c-ai/babysitter context-engineeringInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add a5c-ai/babysitter --skill context-engineering -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/a5c-ai/babysitter.git skills-src && mkdir -p .github/skills && cp -r skills-src/library/methodologies/gsd/skills/context-engineering .github/skills/context-engineering && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "context-engineering" agent skill from https://github.com/a5c-ai/babysitter/tree/main/library/methodologies/gsd/skills/context-engineering into .github/skills/context-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add a5c-ai/babysitter --skill context-engineering -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install a5c-ai/babysitter context-engineering --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/a5c-ai/babysitter.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/library/methodologies/gsd/skills/context-engineering .opencode/skills/context-engineering && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "context-engineering" agent skill from https://github.com/a5c-ai/babysitter/tree/main/library/methodologies/gsd/skills/context-engineering into .opencode/skills/context-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
context-engineering- GitHub stars
- 1.8k
- Token cost
- ~1.8k tokens
- SKILL.md length
- 527 words
- Files
- 2
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- MIT
At a glance
Context window monitoring and budget management. An agent skill from a5c-ai/babysitter.
- Works in 7 steps: Context Usage Estimation → Threshold Warnings → Orchestrator Budget Enforcement → …
- Tasks that involve Context engineering
- SKILL.md covers Capabilities, Tool Use Instructions, Process Integration and Output Format, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Context Engineering is an agent skill from a5c-ai/babysitter. Context window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full 200k tokens. Provides warnings at thresholds, context-aware summarization triggers, and wave-level budget planning.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).
It sits in Agent Workflows, covering Context engineering, Summarization and Budgeting and forecasting. The repository describes itself as: Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration. The licence is MIT.
When your agent uses it
- Tasks that involve Context engineering
- Tasks that involve Summarization
- Tasks that involve Budgeting and forecasting
Example prompts
- “/context-engineering”
Requirements
- Pre-approved tools (allowed-tools): Read, Bash(*)
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit feb68ab. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadBash(*)
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Context Engineering loads about 1.8k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 527 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Read, Bash(*)
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from a5c-ai/babysitter at commit feb68ab, republished under its MIT licence (© a5c-ai). 527 words, ~1,812 tokens.
Download SKILL.mdSave it as
.claude/skills/context-engineering/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- context-engineering
- description
- Context window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full 200k tokens. Provides warnings at thresholds, context-aware summarization triggers, and wave-level budget planning.
- allowed-tools
- Read, Bash(*)
- metadata.author
- babysitter-sdk
- metadata.version
- 1.0.0
- metadata.category
- gsd-core
- metadata.backlog-id
- SK-GSD-003
- graph.domains
- domain:software-engineering
- graph.skillAreas
- skill-area:agentic-loops, skill-area:orchestration-loop
- graph.workflows
- workflow:feature-development
- graph.topics
- topic:developer-experience
- graph.roles
- role:tech-lead, role:backend-engineer
- Subagents: Get full 200k tokens of fresh context per spawn.
- Context budget: Plan how much context each wave of execution will consume.
This skill provides:
- Context window usage estimation for the current session
- Warning injection at configurable thresholds (70%, 85%, 95%)
- Orchestrator budget enforcement
- Subagent context allocation recommendations
- Context-aware summarization triggers
- Stale context detection and pruning suggestions
- Wave-level context budget planning
Capabilities
1. Context Usage Estimation
Estimate current context window usage based on conversation history size:
Tokens used: ~45,000 / 200,000
Usage: 22.5%
Status: HEALTHY
Next threshold: 70% (warning) at ~140,000 tokensEstimation methods:
- Character count / 4 (rough approximation)
- Tool output tracking (each tool call adds to context)
- File read accumulation tracking
2. Threshold Warnings
Inject warnings at configurable thresholds:
[CONTEXT 70%] Warning: Context window at 70%. Consider summarizing completed work.
[CONTEXT 85%] Critical: Context window at 85%. Spawn new subagent for remaining work.
[CONTEXT 95%] Emergency: Context window at 95%. Wrap up immediately. Write state and exit.Actions per threshold:
- 70%: Suggest summarizing completed work, pruning stale context
- 85%: Strongly recommend spawning new subagent with fresh context
- 95%: Emergency wrap-up: write STATE.md, commit, create continue-here.md
3. Orchestrator Budget Enforcement
Monitor orchestrator-specific budget:
Target orchestrator usage: 15-30%
Current orchestrator usage: 18%
Remaining budget: 12% (~24,000 tokens)
Budget allocation:
- Phase context loading: 5% (PROJECT, ROADMAP, STATE)
- Agent spawn overhead: 3% per agent
- Result processing: 2% per agent result
- State updates: 1%4. Subagent Context Allocation
Recommend context allocation for subagent spawns:
Agent: gsd-executor
Available context: 200,000 tokens (fresh)
Recommended loading:
- Plan file: ~2,000 tokens
- Relevant source files: ~15,000 tokens
- Project context: ~3,000 tokens
- Remaining for execution: ~180,000 tokens5. Context-Aware Summarization
Trigger summarization when context is filling:
Summarization triggers:
- Tool output > 10,000 characters: summarize before continuing
- File read > 5,000 lines: extract relevant sections only
- Agent result > 20,000 characters: summarize key outcomesSummarization strategies:
- Completed work: Replace detailed execution logs with summary
- File contents: Replace full file reads with relevant excerpts
- Agent results: Extract key outcomes, discard detailed reasoning
6. Stale Context Detection
Identify context that is no longer relevant:
Stale context candidates:
- File contents read 10+ interactions ago
- Agent results from completed (not current) phases
- Tool outputs that were informational only
- Research documents already synthesized into plans7. Wave-Level Budget Planning
Plan context budget across execution waves:
Wave 1 (3 parallel agents):
Spawn cost: 3 * 3% = 9%
Result processing: 3 * 2% = 6%
Wave total: 15%
Wave 2 (2 parallel agents):
Spawn cost: 2 * 3% = 6%
Result processing: 2 * 2% = 4%
Wave total: 10%
Total orchestrator budget needed: 25%
Target: 30% -> Sufficient with 5% marginTool Use Instructions
Checking Context Usage
- Use
Bashto estimate current session token count if available - Track cumulative tool output sizes during the session
- Calculate percentage against 200,000 token window
- Return usage report with threshold proximity
Injecting Warnings
- Compare current usage against configured thresholds
- If threshold exceeded, format appropriate warning message
- Include recommended action based on threshold level
- For 95%: include emergency state-save instructions
Planning Wave Budgets
- Use
Readto load plan files for the phase - Count agents needed per wave
- Estimate per-agent spawn and result cost
- Sum wave costs and compare to orchestrator budget target
- Recommend wave splitting if budget exceeded
Show full SKILL.md (206 more words)Show less
Process Integration
execute-phase.js- Monitor context during multi-wave execution, trigger summarization between wavesiterative-convergence.js- Track context across convergence iterations, spawn fresh agents when context fillsnew-project.js- Budget context for parallel research agents (4 spawns + synthesis)
Output Format
{
"operation": "check|warn|plan|summarize",
"status": "healthy|warning|critical|emergency",
"usage": {
"estimatedTokens": 45000,
"maxTokens": 200000,
"percentage": 22.5,
"nextThreshold": 70
},
"recommendation": "Continue normally|Summarize completed work|Spawn new agent|Emergency wrap-up",
"waveBudget": {
"totalWaves": 2,
"estimatedOrchestratorUsage": 25,
"withinBudget": true
}
}Configuration
| Setting | Default | Description |
|---|---|---|
contextWarningThreshold | 70 | Warning threshold percentage |
contextCriticalThreshold | 85 | Critical threshold percentage |
contextEmergencyThreshold | 95 | Emergency threshold percentage |
orchestratorBudgetTarget | 30 | Target max orchestrator context % |
agentSpawnCost | 3 | Estimated % per agent spawn overhead |
agentResultCost | 2 | Estimated % per agent result processing |
autoSummarize | true | Auto-trigger summarization at thresholds |
Error Handling
| Error | Cause | Resolution |
|---|---|---|
Token estimation inaccurate | Approximation drift | Use conservative estimates (overestimate usage) |
Budget exceeded mid-wave | Underestimated agent costs | Defer remaining agents to next session with continue-here.md |
Emergency threshold hit | Orchestrator doing too much work inline | Immediately write state, commit, create handoff document |
Stale context false positive | Context still needed | Maintain a "pinned context" list that is never pruned |
Constraints
- Token estimates are approximations (character/4 heuristic); always err on the side of caution
- Never discard context that has not been persisted to disk (STATE.md, summaries, etc.)
- Orchestrator should never exceed 30% context usage
- Emergency wrap-up at 95% is non-negotiable; quality degrades severely above this
- Wave budget planning must account for worst-case agent result sizes
- Context monitoring is advisory; it cannot forcibly stop execution
© a5c-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in library/methodologies/gsd/skills/context-engineering of a5c-ai/babysitter.
- SKILL.md
- README.md
Open the folder on GitHubat commit feb68ab
Compare with similar skills
Context Engineering next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Context Engineering this skilla5c-ai/babysitter | 1.8k | — | ~1.8k | Automated safety check: Notes | MIT | |
| Claude Statusbarleeguooooo/claude-code-usage-bar | 377 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Badstephenleo/bmad-autonomous-development | 107 | — | ~7.7k | Automated safety check: Pass | MIT | |
| Analyze Trajectoryyologdev/yoyo-evolve | 1.9k | — | ~3.6k | Automated safety check: Pass | MIT | |
| Code Context Slicingtrailofbits/skills | 7.4k | — | ~2.1k | Automated safety check: Pass | CC-BY-SA-4.0 | |
| MoAI Foundation Coremodu-ai/moai-adk | 1.2k | — | ~5k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Bad
stephenleo/bmad-autonomous-development
BMad Autonomous Development — orchestrates parallel story implementation pipelines.
Analyze Trajectory
yologdev/yoyo-evolve
Diagnoses a recurring failure such as a stuck task, repeated CI error or frequent reverts by sending sub-agents through the logs and returning one root-cause diagnosis.
- Official
Code Context Slicing
trailofbits/skills
Picks a small, graph-based slice of source with Trailmark and hands a focused code task to a smaller or local model without exposing the whole repository.
MoAI Foundation Core
modu-ai/moai-adk
Reference for MoAI-ADK's core development principles: TRUST 5 quality gates, SPEC-first domain-driven workflow, agent delegation and token budgeting.
Cc Dev Agent
sangrokjung/claude-forge
A skill your agent uses when starting Claude Code projects, writing CLAUDE.md/spec.md, dispatching subagents, or requesting Agent Teams parallel development.
More from a5c-ai/babysitter
All 14 skills in this repoAWS DrawIO Diagram Generator
a5c-ai/babysitter
Creates and edits AWS architecture diagrams as DrawIO XML, converting a text description or an image and reading existing files back into shapes.
GCP DrawIO Diagram Generator
a5c-ai/babysitter
Creates DrawIO XML diagrams of Google Cloud architectures from text or images, and analyzes existing .drawio files to list their GCP components.
Babysitter Run Orchestrator
a5c-ai/babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter…
Babysitter Process Runner
a5c-ai/babysitter
Execute via @babysitter. Use this skill when asked to babysit a task, do anything that is structured process-driven (even a loop) or whenever it is called…
Assimilate Popular Workflows
a5c-ai/babysitter
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns"…
Babysit Babysitter Issues
a5c-ai/babysitter
This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues…
Related
Categories
Questions about Context Engineering
What does Context Engineering do?
Context window monitoring and budget management. An agent skill from a5c-ai/babysitter. Context Engineering is an agent skill from a5c-ai/babysitter. Context window monitoring and budget management.
When should I use Context Engineering?
Context Engineering fits situations like: tasks that involve Context engineering; tasks that involve Summarization; tasks that involve Budgeting and forecasting.
How do I install Context Engineering in Claude Code?
Run `npx skills add a5c-ai/babysitter --skill context-engineering -a claude-code`. Or copy the skill folder (library/methodologies/gsd/skills/context-engineering in a5c-ai/babysitter) into .claude/skills/context-engineering in your project. Claude Code loads it when a task matches its description.
How do I install Context Engineering in Codex?
Run `npx skills add a5c-ai/babysitter --skill context-engineering -a codex`. Or copy the skill folder (library/methodologies/gsd/skills/context-engineering in a5c-ai/babysitter) into .agents/skills/context-engineering in your project. Codex loads it when a task matches its description.
Can I use Context Engineering in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add a5c-ai/babysitter --skill context-engineering -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/context-engineering, .gemini/skills/context-engineering, .github/skills/context-engineering and .opencode/skills/context-engineering in your project.
What does Context Engineering need to run?
SKILL.md names no scripts, command-line tools or credentials: Context Engineering is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Bash(*).
Does Context Engineering access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Context Engineering safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Context Engineering use?
Context Engineering is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Context Engineering use?
About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Context Engineering?
Skills that share tags, products or a category with Context Engineering: Claude Statusbar (leeguooooo/claude-code-usage-bar, 377 stars), Bad (stephenleo/bmad-autonomous-development, 107 stars), Analyze Trajectory (yologdev/yoyo-evolve, 1.9k stars) and Code Context Slicing (trailofbits/skills, 7.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Context Engineering?
a5c-ai (a GitHub organization) maintains it in a5c-ai/babysitter, which has 1,833 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 16, 2026.
Source: a5c-ai/babysitter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.