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.
git clone --depth 1 https://github.com/evan043/claude-cli-advanced-starter-packWrote 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/commands/evan043/claude-cli-advanced-starter-pack/vision-adjust.template)<a href="https://agentmods.dev/commands/evan043/claude-cli-advanced-starter-pack/vision-adjust.template"><img src="https://agentmods.dev/badge/commands/evan043/claude-cli-advanced-starter-pack/vision-adjust.template.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 5.1 | $0.00000 | $0.06694 |
| Opus 5 | $0.00000 | $0.03347 |
| Sonnet 5 | $0.00000 | $0.01339 |
| Haiku 4.5 | $0.00000 | $0.00669 |
Grade A, and why
vision-adjust.template 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 3d 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 — 884 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Runtime Compatibility
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows:
AskUserQuestion=> ask the user directly in chat.WebSearch/WebFetch=> use available web tools (search_query,open,find) and cite links.Read/Write=> use shell/filesystem tools in this workspace.- Claude-only MCP calls (for example Playwright MCP names) => use available equivalents or clearly state fallback.
- Keep intent and output format identical; only adapt execution mechanics.
description: Adjust Vision plan when drift detected or requirements change options:
- label: "Interactive Adjustment" description: "Step-by-step guided adjustment"
- label: "Quick Fix" description: "Apply specific adjustment immediately"
- label: "Re-plan" description: "Regenerate roadmaps and architecture"
Vision Adjust - Dynamic Plan Adjustment
Adjust Vision plan when drift is detected, requirements change, or execution reveals new constraints. Uses the Phase 7 Orchestrator to maintain alignment between vision and reality.
Adjustment Triggers:
- Drift events with severity HIGH or CRITICAL
- User-requested changes to features or constraints
- Technology decisions need revision
- Roadmap execution reveals blockers
- Architecture needs refactoring
- API contracts need changes
Execution Protocol (Phase 7 Orchestrator Integration)
Step 1: Load Vision and Assess State
import { createOrchestrator, loadVision, formatDriftReport } from '${CWD}/node_modules/claude-cli-advanced-starter-pack/src/vision/index.js';
// Create orchestrator and resume from vision
const orchestrator = createOrchestrator(projectRoot);
const resumeResult = await orchestrator.resume(visionSlug);
if (!resumeResult.success) {
console.error(`Failed to load vision: ${resumeResult.error}`);
return;
}
const vision = resumeResult.vision;
const status = orchestrator.getStatus();
// Legacy import for direct updates
import { loadVision, updateVision } from '${CWD}/node_modules/claude-cli-advanced-starter-pack/src/vision/state-manager.js';
const vision = loadVision(projectRoot, visionSlug);
if (!vision) {
console.log(`Vision not found: ${visionSlug}`);
return;
}
// Calculate current drift severity
const driftSeverity = calculateMaxDriftSeverity(vision.observer.drift_events);
const alignment = vision.observer.current_alignment;
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.
- 3d ago First seen · 884 lines · 0 tokens per session scan A 24661188eb79
vision-adjust.template is a command published in the GitHub repository evan043/claude-cli-advanced-starter-pack (61 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,694 tokens. 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 2026-09-03.
Other commands, from other repositories
init-project
Initialize project with CLAUDE.md template - adaptive detection for new or existing projects.
update-counts
Update all hardcoded counts (skills, agents, marketplace repos/skills) across documentation from filesystem.
update-docs
Scan for recently modified files and update corresponding documentation.
handoff
Create a handoff document for seamless session continuity.
board-csk
Team board — see who holds which item, claim one, hand it over, complete it.
queue
Queue a question or coding task for claude-overnight to run when your limits reset.