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/techwolf-ai/ai-first-toolkit/performance-cyclenpx skills add techwolf-ai/ai-first-toolkit --skill performance-cyclegit clone --depth 1 https://github.com/techwolf-ai/ai-first-toolkitWhat 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 | $0.00067 | $0.01723 |
| Opus 5 | $0.00034 | $0.00861 |
| Sonnet 5 | $0.00013 | $0.00345 |
| Haiku 4.5 | $0.00007 | $0.00172 |
Grade A, and why
performance-cycle 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Cycle Assistant
Principle: "You are responsible." This skill gathers and organises evidence. Rating decisions and development assessments are the manager's alone.
Helps managers prepare evidence-based assessments for performance review cycles. The org's performance framework dimensions measure what was achieved and how the person developed. Organizational values measure how they showed up while doing it.
When to Use
- During full review cycles (per the org's review cadence)
- During lighter check-ins between full reviews
- When the manager says "help me prep [name]'s review", "gather evidence for [name]'s performance"
- Can be run for one team member or all reports in batch
Context: Performance Framework
Load the org's performance framework from manager-context/performance-framework.md (created during /setup). This defines:
- Framework dimensions and sub-dimensions
- Rating scale
- Promotion readiness labels (if tracked)
- Review cadence
If manager-context/performance-framework.md doesn't exist, ask the manager to run /setup first.
Instructions
If any MCP connector is unavailable, follow the connector unavailability protocol in references/operating-principles.md.
1. Identify Scope
Determine who to prepare for:
- Single team member: "prep [name]'s review"
- Whole team: "prep all reviews" (runs sequentially for each report)
Determine the review period:
- Default: last 6 months (for bi-annual review) or last 3 months (for check-in)
- Can be customised: "since [date]"
2. Load Context
For the target team member, read from manager-context/team/[name].md:
- Their goals (locations in Notion/Drive)
- Their development areas from last review
- Their role and level (from Job Architecture)
- Their projects and responsibilities
Also load:
manager-context/performance-framework.md: org-specific framework dimensions and rating descriptors (falls back toreferences/performance-framework.mddefaults)manager-context/management-framework.md: org-specific management dimensions (falls back toreferences/management-framework.mddefaults)references/values-guide.md: values definitions and signal guidancemanager-context/values.md: the organization's specific values
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 159 lines · 67 tokens per session scan A dc2523c257f1
performance-cycle is a skill published in the GitHub repository techwolf-ai/ai-first-toolkit (96 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,723 once invoked, about $0.0003 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
snip
You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.
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…
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.
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.
clarify
Adaptive requirements clarification with auto-depth routing. Shallow (Q&A) for simple tasks, Deep (exploration + DRAFT + PLAN) for complex ones. Escalates automatically when ambiguity persists.