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/060-evolvegit 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 | $0.00020 | $0.01944 |
| Opus 5 | $0.00010 | $0.00972 |
| Sonnet 5 | $0.00004 | $0.00389 |
| Haiku 4.5 | $0.00002 | $0.00194 |
Grade A, and why
060-evolve 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evolve — Session Learning Extraction
Extract patterns from session history into reusable learnings. Three modes of operation.
Prerequisites
- Persistence gate:
persistence: truemust be set in Session Config. If not, abort: "Learnings require persistence to be enabled in Session Config." - Session history must exist at
.orchestrator/metrics/sessions.jsonl - Learnings are stored at
.orchestrator/metrics/learnings.jsonl - Config field:
learning-expiry-days(default: 30) — controlsexpires_atfor new and updated learnings
Cursor Adaptation
No AskUserQuestion tool on Cursor. Present all choices as numbered Markdown lists:
Which learnings should be saved?
1. [fragile-file] src/lib/auth.ts — Changed in 4 of last 5 sessions (confidence: 0.5 new)
2. [scope-guidance] optimal-scope-per-session-type — 3 issues/session works well (+0.15 update)
3. Skip all — do not save any learnings
Reply with the number(s) of your choice.
Mode Selection
Determine mode from user input (default: analyze):
| Mode | Purpose |
|---|---|
analyze |
Extract new learnings from session history |
review |
Edit/manage existing learnings interactively |
list |
Display active learnings (read-only) |
Mode 1: Analyze
Extract learnings from .orchestrator/metrics/sessions.jsonl.
Step 1: Load Session Data
- Read all entries from
sessions.jsonl, parse each line as JSON - Sort by
completed_atdescending (most recent first) - If no sessions found, abort: "No session data available."
Step 2: Pattern Extraction
Apply these heuristics for each learning type:
fragile-file
- Same file appears in 3+ waves'
files_changedwithin a session, or in 3+ different sessions - Subject = relative file path
effective-sizing
- Compare
total_agentsandtotal_wavesacross session types - Calculate average agents per wave per session type
- Subject = e.g.
deep-session-sizingorfeature-session-sizing
recurring-issue
agent_summaryshowsfailedorpartial> 0 across multiple sessions- Repeated failures in wave
qualityfields - Subject = issue pattern identifier (e.g.
test-failures-in-wave-execution)
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 · 233 lines · 20 tokens per session scan A 32530add58ab
060-evolve is a cursor rule published in the GitHub repository Kanevry/session-orchestrator (49 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 1,944 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
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.
design-systems
Design system mechanics: tokens, shadcn/ui, Tailwind v4, composition, theming. Load for UI implementation — aesthetics and anti-slop live in the anti-slop-design skill.
model-compatibility
Model compatibility guide: prompt hierarchy, M3-first model selection, tool discipline, read-before-edit safety, and context control across models.
devops-infrastructure
DevOps and infrastructure: Docker, Kubernetes, Terraform, CI/CD. Load when editing Dockerfiles, compose, k8s manifests, Terraform, or workflow YAML — not for application code.
conventional-commits
Always use Conventional Commits for git commit messages.