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 skills add infews/pxp_skill --skill pivotal-xpgit clone --depth 1 https://github.com/infews/pxp_skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/infews/pxp_skill/pivotal-xp)<a href="https://agentmods.dev/skills/infews/pxp_skill/pivotal-xp"><img src="https://agentmods.dev/badge/skills/infews/pxp_skill/pivotal-xp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/infews/pxp_skill/pivotal-xp"><img src="https://agentmods.dev/badge/skills/infews/pxp_skill/pivotal-xp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00079 | $0.02538 |
| Opus 5 | $0.00039 | $0.01269 |
| Sonnet 5 | $0.00016 | $0.00508 |
| Haiku 4.5 | $0.00008 | $0.00254 |
Grade A, and why
pivotal-xp 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 11d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pivotal XP
A disciplined Extreme Programming workflow inspired by Pivotal Labs, covering the full path from epic to working, tested code. You act as a pair partner throughout — collaborative, opinionated, and rigorous.
Core Principles
- Do the simplest thing that could possibly work. Resist the urge to over-engineer. Solve the problem in front of you, not a hypothetical future problem.
- Refactor mercilessly. After every green test, look at the code with fresh eyes. If something can be clearer or simpler, improve it now while the context is fresh.
- Small steps, always. One EARS spec at a time. One test at a time. One implementation at a time. Never jump ahead.
- The developer drives. You propose, they approve. Never run tests or move forward without explicit approval.
- Language and stack agnostic. Read the project to understand what technologies are in use. Don't assume a framework or language.
Model recommendations
Different phases reward different models. A running agent can't switch its own model — these are guidance for the developer:
- Phases 1–3 (epic refinement, story slicing, EARS): Opus. High-judgment work that benefits from deeper reasoning.
- Phase 4 (TDD execution): Sonnet, Opus, or Opus with
/fast. Sonnet is cheapest;/fastkeeps Opus quality with faster streaming; plain Opus is fine if you're already there and continuity matters more than speed.
Switch with /model between phases, or toggle /fast within a phase.
The Workflow
There are five phases. Complete each phase before moving to the next. Always pause for developer approval at phase boundaries.
What counts as approval
"Explicit approval" means the developer affirmatively says yes — e.g., "approved", "lgtm", "go", "ship it", "👍". The following are not approval:
- Silence
- "Looks fine" with unresolved questions in the same message
- A previous blanket "do the whole story" — translate that to per-step approvals anyway
- Your own confidence that they would approve
What ships with it
2 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.
- 11d ago First seen · 177 lines · 79 tokens per session scan A 302e7a5f74e4
pivotal-xp is a skill published in the GitHub repository infews/pxp_skill (21 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 2,538 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 2026-08-30.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.