A before-and-after checker for Sipcode’s token optimizers, using the user’s own coding-session data. It compares a baseline period with a later period only when the data windows are valid.

Use it to check whether Sipcode changed token usage, output volume, or cost, and to see why a reliable comparison cannot yet be made.

It prevents misleading savings claims when there is not enough post-install data or the comparison periods do not match.

impact — Skill for Claude Code by Anuj7411/sipcode

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.

Any agent

npx skills add Anuj7411/sipcode --skill impact

Clone the repo

git clone --depth 1 https://github.com/Anuj7411/sipcode

Made for: Claude Code.

Or install sipcode, the plugin that ships this one along with the rest of its 8 skills, 1 MCP server.

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/skills/anuj7411/sipcode/impact/github.svg)](https://agentmods.dev/skills/anuj7411/sipcode/impact)

Your own site

<a href="https://agentmods.dev/skills/anuj7411/sipcode/impact"><img src="https://agentmods.dev/badge/skills/anuj7411/sipcode/impact/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/anuj7411/sipcode/impact"><img src="https://agentmods.dev/badge/skills/anuj7411/sipcode/impact.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 488 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00069	$0.00488
Opus 5.5	$0.00028	$0.00195
Sonnet 5.5	$0.00014	$0.00098
Haiku 4.5	$0.00007	$0.00049

Measured 1mo ago against content hash 6b70de52c59f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

impact 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.

skills/impact/SKILL.md · 22 lines

What it actually says

Sipcode — Impact (the savings verifier)

Call the sipcode:verify_sipcode_impact MCP tool to produce a structured before/after comparison.

Critical: respect the integrity contract. The tool's response is structured with these key fields:

status — one of: "measured", "insufficient-post-data", "no-install-marker", "no-baseline", "no-post-sessions", "window-asymmetry-<N>d-vs-<M>d"
delta — present (numbers) ONLY when status === "measured". Null in every other case by design. When delta is null, DO NOT compute a savings number from before/after totals. The windows aren't comparable.
allTime — present only when no marker exists. Contains the user's total session count across all time, so the user sees their data exists even when no A/B split is possible.
warningReason — explains why delta is null (e.g., "window-asymmetry-39d-vs-2d", "insufficient-post-data-2d-vs-min-3d").
headline — the canonical one-line summary; trust this and surface it.

When status === "measured": lead with the output-ratio change (the only normalization-resistant metric). Mention token + dollar savings as secondary. Include the window-length caveat.

When status !== "measured": present the headline and the next-step recommendation from the notes field. Do not invent a savings number. The tool's delta: null is structurally enforced — do not work around it.

If the user pushes back and asks you to compute a number anyway, refuse and explain the structural reason: the comparison windows aren't fair, so any delta would be misleading. Suggest they pass since: "YYYY-MM-DD" to set a manual pivot, or run sipcode rules --install to start measuring forward.

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.

1mo ago First seen · 22 lines · 69 tokens per session scan A 6b70de52c59f

Subscribe to this mod's changes

impact is a skill published in the GitHub repository Anuj7411/sipcode (46 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 488 once invoked, about $0.0003 per session on Opus 5.5. 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.

Analytics and metrics Claude Code ai-coding anthropic ast claude-desktop cli

loongsuite-pilot-insight

A reporting workflow for turning LoongSuite Pilot and AI coding-agent logs into structured reports about events, teams, data quality, development efficiency, and AI use. It defines the meaning of the log fields and the measurements used in dashboards.

alibaba/loongsuite-pilot · 91 tokens

loongsuite-pilot-ops

Skill "loongsuite-pilot-ops" from alibaba/loongsuite-pilot, covering loongsuite-pilot-ops, quick start, todo: add quick start commands and usage.

alibaba/loongsuite-pilot · 15 tokens

atomic-visual-options

Planning-phase visual comparison aid. Renders 2-4 side-by-side variants per decision dimension as a single throwaway, self-contained HTML file and captures the user's pick as typed terminal codes (e.g. "A2 B3"). Auto-fires on phrases like "show me a few options", "mock up some variants", "let me see this side by…

damusix/atomic-claude · 150 tokens

atomic-wiki

Conversational wiki and capture-bucket routing. Fires when the user wants a place, space, or folder for notes, research, tickets, raw dumps, or knowledge capture — checks the block in /.claude/CLAUDE.md; if the cwd is under a registered realm, creates the folder as a bucket via atomic wiki bucket add rather than a…

damusix/atomic-claude · 204 tokens

atomic-review

Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.

damusix/atomic-claude · 63 tokens

atomic-tdd

Test-first discipline. Auto-triggers on "let's implement X", "add feature Y", "fix bug Z", "write a test for", "implement", "build out", and similar pre-code-change phrases. Iron rule: failing test exists before production code. Skip only for pure docs/config changes with an explicit "skipped because:" note. Explicit…

damusix/atomic-claude · 142 tokens