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/soden46/engineer-flow/performancenpx skills add soden46/engineer-flow --skill performancegit clone --depth 1 https://github.com/soden46/engineer-flowWhat 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 | $0.00035 | $0.00473 |
| Opus 5 | $0.00017 | $0.00236 |
| Sonnet 5 | $0.00007 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
performance 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance
Use this skill when work involves latency, throughput, resource usage, query efficiency, rendering cost, memory pressure, or scaling bottlenecks.
This skill is technology agnostic.
Measure First
Do not optimize solely from intuition.
Identify:
- the slow operation
- current baseline
- dominant cost
- expected improvement
- acceptable tradeoffs
Use measurements appropriate to the system.
Common Bottlenecks
Investigate relevant:
- repeated database queries
- N+1 access
- unnecessary network calls
- repeated computation
- inefficient algorithms
- excessive serialization
- large payloads
- blocking I/O
- unnecessary rendering
- memory growth
- contention
- cache misses
- excessive file operations
Do not assume the database is always the bottleneck.
Database Performance
Consider:
- query count
- query plans
- indexes
- join behavior
- selected columns
- pagination
- batch operations
- eager/bulk loading
- connection usage
Add indexes based on actual query patterns.
Caching
Cache when:
- computation or retrieval is meaningfully expensive
- reuse is likely
- consistency requirements are understood
Define:
- cache key
- lifetime
- invalidation
- ownership
- failure behavior
Do not add caching merely to hide an inefficient design without understanding correctness implications.
Memory
Avoid loading unbounded datasets into memory.
Prefer:
- streaming
- chunking
- pagination
- iterators
- bounded batches
when processing large data.
Concurrency
Parallelism can improve throughput but may increase:
- contention
- memory usage
- rate-limit pressure
- database load
- ordering complexity
Use bounded concurrency.
Verification
Compare before and after.
Verify:
- functional behavior remains correct
- measured metric improves
- resource usage remains acceptable
- no significant regression is introduced elsewhere
Performance work without measurement should be treated as a hypothesis, not a proven optimization.
Framework Adaptation
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 · 126 lines · 35 tokens per session scan A c0015bc52711
performance is a skill published in the GitHub repository soden46/engineer-flow (3 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 473 once invoked, about $0.0002 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 skills, from other repositories
snip
You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
reviewing-changes
Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.
setting-up-a-project
Use whenever asked to set up, onboard, initialize, or spec a project — the front door when the workspace has no spec graph yet (brand-new or an existing codebase); also seeded by the app's Set-up-project card (/skill:setting-up-a-project). Not for feature work in an already-specced project — use the brainstorming…
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.