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/mtthsnc/tempest/plannpx skills add mtthsnc/tempest --skill plangit clone --depth 1 https://github.com/mtthsnc/tempestWhat 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 | $0.00071 | $0.00813 |
| Opus 5 | $0.00036 | $0.00407 |
| Sonnet 5 | $0.00014 | $0.00163 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
plan 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan — produce a reviewed implementation plan
Overview
The front of the factory. Turn a task into a plan that is concrete enough to execute and honest about its risks — before any code is written. A good plan names the files it will touch, reuses what already exists, and has survived its own strongest objection.
This is a STARTER skill — a generic spine. Rewrite the procedure and the review lenses below to encode your own engineering opinions and standards.
The plan is the output. You do not implement here; you produce a plan a build step can follow.
Procedure
1. Understand before proposing
- Restate the task in one sentence. If that sentence is ambiguous, ask the user now — a wrong assumption is cheapest to fix here.
- Explore the codebase for existing functions, utilities, and patterns that already do part of this. Prefer reusing them over writing new code. Note the concrete file paths.
- Identify the smallest change that fully satisfies the task.
2. Draft the plan
Write a plan with these parts:
- Context — why this change, what problem it solves, the intended outcome.
- Approach — the recommended approach only (not a survey). Name the trade-off you accepted.
- Changes — the files to create/modify, each with a one-line description of what changes. For a pattern repeated across many files, describe it once and list a few representative paths.
- Reuse — existing functions/utilities (with paths) the build should call instead of reinventing.
- Verification — how to prove it works end-to-end: the command to run, the test to add, the behavior to observe.
- Risks / unknowns — what could go wrong and what you are unsure about.
3. Review it against itself
Before presenting, attack your own plan from these lenses (collapse or extend to taste):
- Correctness — does it actually satisfy the restated task? Any missed case?
- Scope — is anything in here not required? Cut it. Is anything required missing? Add it.
- Simplicity / reuse — is there an existing pattern that makes a chunk of this unnecessary?
- Reversibility — if this is wrong, how hard is it to undo? Prefer the more reversible path.
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 · 64 lines · 71 tokens per session scan A ba777c3e1c77
plan is a skill published in the GitHub repository mtthsnc/tempest (2 stars, last pushed 2mo ago), licensed MIT. It adds 71 tokens to every session and 813 once invoked, about $0.0004 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
codebase-memory
Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions…
using-pi-subagents
Operate pi-subagents jobs safely, including direct-work decisions, least-privilege tool selection, thinking-level selection, delegation, bidirectional messaging, parallel starts, timeout selection, waiting, cancellation, result handling, verification, and writer isolation.
improvement-discovery
Heuristics and process for discovering structural improvements in this package. Load when planning a new improvement round — contains the smell taxonomy, analysis workflow, and prioritization framework distilled from many phases of refactoring.
fabric-workflow
Runs a dynamic Pi Fabric workflow with code-held phases, fan-out, pipelines, structured agents, and best-effort verification. Use for large audits, migrations, parallel research, or explicit workflow requests.
fabric-spec
Starts a persistent Pi Fabric spec supervisor that audits the main session against a feature design spec and steers only when a requirement lacks verified evidence. Use for strict, unblocked spec compliance while the main agent keeps full freedom to orchestrate.
surf
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.