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 skills/mountainunicorn/add/optimizenpx skills add MountainUnicorn/add --skill optimizegit clone --depth 1 https://github.com/MountainUnicorn/addWhat 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 | $0.00017 | $0.03628 |
| Opus 5 | $0.00009 | $0.01814 |
| Sonnet 5 | $0.00003 | $0.00726 |
| Haiku 4.5 | $0.00002 | $0.00363 |
Grade A, and why
optimize 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 yesterday.
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 — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADD Optimize Skill v{{VERSION}}
Identify and fix performance bottlenecks. This skill profiles code to find slow operations, suggests optimizations, and implements them with test-driven discipline.
Overview
The Optimize skill improves application performance while maintaining correctness. It:
- Profiles code to identify bottlenecks
- Quantifies performance issues
- Suggests targeted optimizations
- Implements with TDD (tests before optimization)
- Verifies improvements with measurements
- Documents optimizations for future maintainers
Performance optimization follows TDD discipline: write tests that capture performance expectations before implementing optimizations.
Pre-Flight Checks
-
Verify implementation exists
- Identify implementation files (src/, app/, etc.)
- Verify code is in GREEN state (all tests passing)
- Halt if tests not passing (optimize only stable code)
-
Load configuration
- Read .add/config.json
- Extract performance targets:
- perf.pageLoadTime (e.g., < 2 seconds)
- perf.responseTime (e.g., < 100ms)
- perf.memoryLimit (e.g., < 50MB)
- perf.bundleSize (e.g., < 500KB)
-
Determine scope
- Use --scope flag to target: backend, frontend, or full
- Default: full system
- Scope guides which profiling tools to use
-
Check for profiling data
- If --profile-first: profile before optimization
- Otherwise, use existing profile if available
- Or ask user for baseline metrics
-
Identify profiling tools
- Backend: py-spy, perf, go pprof, node --prof, etc.
- Frontend: Chrome DevTools, Lighthouse, WebPageTest
- Database: EXPLAIN ANALYZE, pg_stat_statements, etc.
-
Check for session handoff — per the Session-Handoff Preflight in
${CLAUDE_PLUGIN_ROOT}/references/skill-epilogue.md
Execution Steps
Step 1: Baseline Profiling (if --profile-first)
Establish baseline measurements:
For Backend (Python):
# Profile with py-spy
py-spy record -o profile.svg -- python -m pytest tests/
# Or use cProfile
python -m cProfile -s cumulative app.py > profile.txt
# Database queries
EXPLAIN ANALYZE SELECT ...
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.
- yesterday First seen · 510 lines · 17 tokens per session scan A 97e49bdb7f84
optimize is a skill published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 3,628 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 skills, from other repositories
swarm
Launching multi-agent parallel work with the Agentic SDLC. Use when a task benefits from decomposition into parallel subtasks.
finish
Completing a development branch for merge readiness. Use when implementation and tests pass and the branch needs formal preparation for review and merge.
grill
Interrogating requirements to validate before building. Use before swarm decomposition, design decisions on ambiguous features, or when scope creep risk is high.
team
Referencing the agent roster, roles, coordination model, and dispatch modes. Use when spawning agents or checking permissions.
ticket
Associate every PDS task with a GitHub issue. Orchestrator finds or creates the ticket, posts plan and acceptance criteria as a checkbox list, updates it as work progresses. Use at Phase 1 of every swarm.
triage
Triage insights into actionable GitHub issues across repos. Use after running /insights to convert analysis into tracked work.