stats-newpr

Install

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.

agentmods

npx agentmods add commands/blpsoares/agentistics/stats-newpr

Clone the repo

git clone --depth 1 https://github.com/blpsoares/agentistics

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/blpsoares/agentistics/stats-newpr.svg)](https://agentmods.dev/commands/blpsoares/agentistics/stats-newpr)

Your own site

<a href="https://agentmods.dev/commands/blpsoares/agentistics/stats-newpr"><img src="https://agentmods.dev/badge/commands/blpsoares/agentistics/stats-newpr.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 780 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00780
Opus 5	$0.00000	$0.00390
Sonnet 5	$0.00000	$0.00156
Haiku 4.5	$0.00000	$0.00078

Measured 2d ago against content hash 111375ae9581, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stats-newpr 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.

.claude/commands/stats-newpr.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the full pre-PR checklist for claude-stats, then open the pull request.

Language

Everything must be in English: PR title, PR body, commit messages, and any code comments added in this change. This is non-negotiable.

Step 1 — Run tests

Run bun test. All tests must pass with 0 failures before proceeding. If any fail, fix them first.

Step 2 — Context-aware checks

Inspect what changed in this branch and run only the relevant checks below.

If any cost calculation was touched (calcCost, getModelPrice, MODEL_PRICING, blendedCostPerToken):

Verify MODEL_PRICING in src/lib/types.ts and FALLBACK_PRICING in server.ts are in sync (same models, same prices)
Verify the per-layer cost table in CLAUDE.md is still accurate

If a new model was added:

MODEL_PRICING in src/lib/types.ts
FALLBACK_PRICING in server.ts
PRICING_PAGE_MODEL_MAP in server.ts (for live price scraping)
CLAUDE.md pricing section

If a new exported pure function was added:

Confirm there is a corresponding test in the relevant .test.ts file
If not, write the missing test cases before opening the PR

If streak, date filtering, or timezone logic was touched:

Confirm the fix uses format(date, 'yyyy-MM-dd') (local time) not toISOString().slice(0, 10) (UTC)
Confirm activeDates is built from both dailyActivity and data.sessions

If the stats-cache schema changed (new fields in StatsCache, SessionMeta, DailyActivity):

Note it explicitly in the PR as a potential breaking change for users upgrading

If a UI component changed (charts, cards, heatmap, PDF export):

Add a screenshot or short description of the visual diff to the PR body

If data aggregation or session parsing was touched (parseSessionJsonl, useDerivedStats):

Note any performance impact (more/fewer file reads, heavier compute per session)

Step 3 — Documentation

CLAUDE.md — update if any of the following changed:

A function in the per-layer cost table
A new "important rule" about data behavior
The data flow or architecture

Read the full file on GitHub · 82 lines

Changes

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 · 82 lines · 0 tokens per session scan A 111375ae9581

Subscribe to this mod's changes

stats-newpr is a command published in the GitHub repository blpsoares/agentistics (39 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 780 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 2026-09-01.

Git and workflow agents agents-skills ai llm-metrics metrics

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Language

Step 1 — Run tests

Step 2 — Context-aware checks

Step 3 — Documentation

What this file has done since we first saw it

Other commands, from other repositories

project-hierarchy-check

security-validation

ctx:stats

README

test-coroot-natural

git