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 rules/kanevry/session-orchestrator/010-session-workflowgit clone --depth 1 https://github.com/Kanevry/session-orchestratorWhat 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 | $0.00025 | $0.01522 |
| Opus 5 | $0.00013 | $0.00761 |
| Sonnet 5 | $0.00005 | $0.00304 |
| Haiku 4.5 | $0.00003 | $0.00152 |
Grade A, and why
010-session-workflow 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Workflow
This rule is an index, not the procedure. Canonical skills:
/session→ Readcommands/session.md, thenskills/session-start/SKILL.md/go→ Readcommands/go.md, thenskills/wave-executor/SKILL.md/close→ Readcommands/close.md, thenskills/session-end/SKILL.md
Cursor has no Skill tool. Follow those files exactly. The summary below is not a substitute.
Three-phase workflow: Start -> Execute -> Close.
Phase 1: Session Start (/session [type])
Session types:
- housekeeping — git cleanup, docs, CI health, dependency updates
- feature — implementation of issues/features
- deep — thorough work requiring extended focus
Step 1: Read Session Config
Parse ## Session Config from project's CLAUDE.md. Store as $CONFIG.
Step 2: Session Continuity
If persistence is enabled, check .cursor/STATE.md:
status: active— crashed session. Ask: "Found unfinished session. Resume or start fresh?"status: paused— intentional pause. Offer to resume or start fresh.status: completed— note summary for context, continue normally.- Missing — first session, continue normally.
Step 3: Git Analysis
Run in parallel:
# Branch state
git branch -a && git log --oneline -20
# Unpushed/uncommitted work
git status --short
git log origin/main..HEAD --oneline
# Stale branches (no commits in 7+ days)
git for-each-ref --sort=-committerdate --format='%(refname:short) %(committerdate:relative)' refs/heads/
Step 4: VCS Deep Dive
Query open issues, recent closures, milestones, MRs/PRs, CI status:
# GitLab
glab issue list --per-page 50
glab issue list --closed --per-page 10
glab mr list --per-page 20
# GitHub
gh issue list --limit 50
gh pr list --limit 20
Group issues by priority (critical/high first) and session-type relevance.
Step 5: Environment Check
# Quality baseline (non-blocking)
{typecheck-command} 2>&1 | tail -5
{test-command} 2>&1 | tail -5
Check SSOT file freshness. Flag files older than 5 days.
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 · 179 lines · 25 tokens per session scan A 651f8b39ebea
010-session-workflow is a cursor rule published in the GitHub repository Kanevry/session-orchestrator (49 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 1,522 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 2026-08-30.
Other cursor rules, from other repositories
language-agnostic-patterns
Language-agnostic programming patterns: SOLID, design patterns, clean code, and architecture. Load when refactoring, designing abstractions, or reviewing structure — not for everyday syntax.
cursor-tools-mastery
Cursor 3.7 runtime guide: choose the right tool, canvases, Design Mode, /worktree, /best-of-n, Await, and parallel execution where safe.
kandev-pr-fixup
Kandev PR fixup workflow prompt for Cursor agents.
cursor-agent-orchestration
Cursor 3.7 orchestration guide: when to plan, when to delegate, nested subagents, multi-environment handoffs, /best-of-n, and Await for long-running branches.
fable5-reasoning
Fable 5 reasoning protocols: task interpretation, risk-first decomposition, approach selection, interleaved thinking, hypothesis ledgers, premortems, calibration, and the stuck-strategy ladder. Load for complex, ambiguous, or long-horizon tasks, for debugging strategy, or whenever progress stalls.
cursor-mcp-optimization
Cursor 3.7 MCP optimization: browser Design Mode, canvases, Figma, Cloudflare tools, MCP Apps structured content, and direct action patterns.