Borrowing it
Nothing to install: this file belongs to friedbotstudio/baseline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/friedbotstudio/baseline/main/.claude/skills/power/SKILL.mdgit clone --depth 1 https://github.com/friedbotstudio/baselineWrote 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/friedbotstudio/baseline/power)<a href="https://agentmods.dev/skills/friedbotstudio/baseline/power"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/power/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/friedbotstudio/baseline/power"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/power.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.00915 |
| Opus 5.5 | $0.00000 | $0.00366 |
| Sonnet 5.5 | $0.00000 | $0.00183 |
| Haiku 4.5 | $0.00000 | $0.00092 |
Grade A, and why
power 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 1mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
power — batch-sprint track behaviours
The power track (in .claude/workflows.jsonl) delivers a sprint of related, spec-committed tickets in
ONE cycle. It reuses the standard phase skills; this skill hosts the two behaviours that make it a batch
pipeline rather than a single-ticket one. It is invoked from within a power-track workflow — never
standalone.
Precondition
project.json → velocity.power_mode.enabled is true, track_id is power, the project is a git repo,
and workflow.json → tickets[] lists the batch (the epic sliced-spec shape: one entry per ticket, each
with its AC group + done-record). Off-flag, power is not selectable and nothing here runs.
Behaviour 1 — per-ticket judgment, amortized mechanics
The mechanical phases — spec, simplify, integrate, document, archive, and the commit-consent
gate — run once for the batch. The judgment phase — security — runs once per ticket: the phase
skill loops over workflow.json → tickets[], running its review for each ticket's AC group and write
surface, and records a per-ticket verdict in the harness log (power_batch_reviews). This is a static DAG
with in-skill iteration — there is no runtime node fan-out (the materializer cannot expand a runtime-sized
list).
The amortization is mechanical-only and structurally visible — a per-ticket security review is never
silently skipped. If any ticket's security raises a BLOCKER, the batch yields for it exactly as a
single-ticket workflow would.
Behaviour 2 — commit split (closure last)
At the commit phase, the batch's working tree is split into a series of small, reviewable Conventional
Commits so per-commit reviewability (bisect/revert) is preserved even though the cycle is large.
commit-split.mjs composes on commit-planner's groupDirtyTree (single-concern grouping) and adds the
power-specific ordering + closure-last rule. Feed it the dirty tree as [{path, status}] (the same shape
groupDirtyTree consumes — parse it from git status --porcelain):
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.
- 1mo ago First seen · 61 lines · 0 tokens per session scan A af6babda49d3
power is a skill published in the GitHub repository friedbotstudio/baseline (14 stars, last pushed 13d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 915 tokens. 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
code-review-with-lsp
Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.
i18n-check
An internationalization (i18n) check for software that supports multiple languages. It compares translation files with the text and translation keys used by the code.
vue-best-practices
A review checklist for Vue 2 and Vue 3 components, covering component names, prop declarations, TypeScript casts, API styles and complex template expressions.
gdpr-audit
GDPR compliance audit of code, plans, schemas, or IaC. Produces a findings report with article citations, severity, confidence, and fixes; flags evidence gaps. Not a substitute for a DPO/lawyer.
cognitive-walkthrough
Deep-dive usability evaluation of specific user tasks. Simulates novice user cognition step-by-step to identify learnability issues, unclear actions, and points of confusion.
owasp-ai-testing
AI trustworthiness testing using OWASP AI Testing Guide v1. Execute 32 test cases across 4 layers (Application, Model, Infrastructure, Data) with practical payloads and remediation.