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 commands/parkerm2/create-claude-workflow/extract-contextgit clone --depth 1 https://github.com/ParkerM2/create-claude-workflowWhat 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 | $0.00012 | $0.03594 |
| Opus 5 | $0.00006 | $0.01797 |
| Sonnet 5 | $0.00002 | $0.00719 |
| Haiku 4.5 | $0.00001 | $0.00359 |
Grade A, and why
extract-context 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 2d 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 — 571 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract Context Command
Captures and persists all valuable knowledge from ticket work: technical decisions, blockers, code patterns, gotchas, and cross-references. Saves to .claude/progress/<ticket>/context-extract.md and optionally to Confluence.
Usage
/extract-context [TICKET_ID] [--confluence] [--memory] [--force]
Options:
TICKET_ID: Jira ticket ID (e.g., PROJ-123). Auto-detect from git branch if omitted.--confluence: Also create/update Confluence page with extracted context--memory: Add key findings to memory system for future conversations--force: Overwrite existing context-extract.md without prompting
Phase 1: Ticket Detection
// Detect ticket ID from branch or user input
const detectTicketId = async (provided) => {
if (provided) return provided;
try {
const branch = await exec('git rev-parse --abbrev-ref HEAD');
const match = branch.match(/([A-Z]+-\d+)/);
if (match) return match[1];
} catch (e) {
// Not in git repo or can't get branch
}
return null;
};
const ticketId = await detectTicketId(args[0]);
if (!ticketId) {
console.error('❌ No ticket ID provided and could not detect from branch');
console.log('Usage: /extract-context PROJ-123');
return;
}
console.log(`\n📋 Extracting context for ${ticketId}...`);
// Load existing progress directory
const progressDir = `.claude/progress/${ticketId}`;
let existingData = {
research: null,
plans: null,
tasks: null
};
try {
if (fs.existsSync(progressDir)) {
const files = fs.readdirSync(progressDir);
if (files.includes('research.md')) {
existingData.research = fs.readFileSync(
`${progressDir}/research.md`, 'utf8'
);
}
if (files.includes('plan.md')) {
existingData.plans = fs.readFileSync(
`${progressDir}/plan.md`, 'utf8'
);
}
if (files.includes('tasks.md')) {
existingData.tasks = fs.readFileSync(
`${progressDir}/tasks.md`, 'utf8'
);
}
}
console.log('✓ Loaded existing progress data');
} catch (e) {
console.log('ℹ️ No existing progress directory');
}
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.
- 2d ago First seen · 571 lines · 12 tokens per session scan A 737031f6ccf1
extract-context is a command published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 3,594 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
speckit.auto
Automatically execute the four core phases of the Spec-Driven Development (SDD) pipeline: specify → plan → tasks → implement, in strict sequential order.
daily-priorities
Query DIGI Jira via the Atlassian MCP to build a prioritized daily work plan. The report has two parts: suggested priorities (the recommendation) and full context (everything you need to evaluate whether the suggestions are right and what else is on the docket).
OPSX: Bulk Archive
Archive multiple completed changes at once.
sync-linear
Sync current work with Linear ticket status.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).