share

A way to turn supported cctally reports into self-contained Markdown, HTML, or SVG files. These files can be pasted into chat, attached to a GitHub issue, or shared as images.

In plain words
What is it for?
Use it with supported reporting commands such as daily, weekly, forecast, budget, project, session, and Codex reports, while reviewing the output before sharing it.
Why use it?
It avoids manually copying tables or rebuilding charts when you need to show usage information to someone else.

Command

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/omrikais/cctally/share
Clone the repo
git clone --depth 1 https://github.com/omrikais/cctally
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 2,999 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02999
Opus 5 $0.00000 $0.01499
Sonnet 5 $0.00000 $0.00600
Haiku 4.5 $0.00000 $0.00300

Measured 2d ago against content hash 77f5b3258bd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

share 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.

docs/commands/share.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shareable reports (--format on reporting commands)

The dashboard ships a GUI for these flags — see share-v2.md. The two paths share the render kernel (bin/_lib_share.py), so formatting, escaping and the provenance line are identical across them. They do not share snapshot builders, so titles, subtitles, column sets and the row axis differ: daily is one row per day on the CLI and one row per project on the dashboard. Do not expect a CLI artifact and a dashboard artifact of the same panel to be byte-identical.

cctally has a cross-command shareable-output surface: the explicitly listed command families below accept a --format {md,html,svg} flag that produces a self-contained artifact suitable for chat paste, GitHub issue, or screenshot. This page is the single reference for the flag surface; per-command pages document the per-command chart and table layouts.

Claude cost coverage: Shared Claude dollar and token totals inherit the transcript-derived lower-bound contract. Codex accounting is unaffected.

Supported subcommands

report, daily, monthly, weekly, forecast, budget, project, five-hour-blocks, session, the four codex-* accounting reports, and the source-aware project, diff, range-cost, cache-report, and report routes — sixteen commands in total. The dashboard has its own share UI; its source selection and share history are documented under Dashboard share source identity below.

For each source-aware command, the flat command and both fixed subgroup forms (cctally claude <command> and cctally codex <command>) expose the same share flags, including --reveal-projects; normal share validation runs before provider reads or output-destination I/O.

Provider identity and privacy

Source-aware CLI artifacts always identify their source. A direct Codex artifact shows Codex; an all-source artifact is composed as exactly two sections, Claude then Codex, rather than a synthetic all source. Empty sections render No data; unavailable sections render Unavailable: <stable reason> and are not silently dropped.

Read the full file on GitHub · 146 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.

  1. 2d ago First seen · 146 lines · 0 tokens per session scan A 77f5b3258bd6

Subscribe to this mod's changes

share is a command published in the GitHub repository omrikais/cctally (5 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,999 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 2026-08-31.