report

report is a skill for Claude Code, Codex from ArcticFox2029/chamnan. It costs 35 tokens per session (253 once invoked), scanned A, original, MIT.

A report of how much text the coding agent carries into each request in one repository, comparing earlier and later periods. It also shows how much new file content is read per request.

In plain words
What is it for?
Reviewing weekly context-per-turn and new-read-per-call history, and stating when there is not enough data for a meaningful comparison.
Why use it?
It helps answer whether the chamnan workspace is reducing context usage, without confusing that with the model's price or unrelated changes in the project.

Skill for Claude CodeCodex

Part of the chamnan plugin — 8 skills, 2 agents, 4 hooks shipped together

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 skills/arcticfox2029/chamnan/report
Any agent
npx skills add ArcticFox2029/chamnan --skill report
Clone the repo
git clone --depth 1 https://github.com/ArcticFox2029/chamnan

Made for: Claude Code, Codex.

Or install chamnan, the plugin that ships this one along with the rest of its 8 skills, 2 agents, 4 hooks.

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.

agentmods badge for report

README.md
[![agentmods](https://agentmods.dev/badge/skills/arcticfox2029/chamnan/report.svg)](https://agentmods.dev/skills/arcticfox2029/chamnan/report)
Your own site
<a href="https://agentmods.dev/skills/arcticfox2029/chamnan/report"><img src="https://agentmods.dev/badge/skills/arcticfox2029/chamnan/report.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 253 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 $0.00035 $0.00253
Opus 5 $0.00017 $0.00127
Sonnet 5 $0.00007 $0.00051
Haiku 4.5 $0.00003 $0.00025

Measured 4d ago against content hash e6718601d8c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

report 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 4d 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/report/SKILL.md · 28 lines

What it actually says

Show the effect, honestly

chamnan-report

Reading it out

The metric is context per call — tokens carried into each API request. That is what a workspace can change. Cost per call is not: it moves when the user switches model, which has nothing to do with this plugin, and quoting it would take credit for something the plugin did not do.

new-read/call is the sharper number. It counts material entering the context for the first time — files being opened. That is exactly what an index is supposed to make unnecessary.

What not to say

Do not present this as proof. The user's model, tasks, and Claude Code itself all changed over the same weeks. It is an observation on one repository, which is the honest and useful thing about it: it is their number, not a figure from someone's README.

If there is not enough history on both sides yet, say that plainly and stop. Do not reach for a comparison the data cannot support.

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. 4d ago First seen · 28 lines · 35 tokens per session scan A e6718601d8c6

Subscribe to this mod's changes

report is a skill published in the GitHub repository ArcticFox2029/chamnan (4 stars, last pushed 6d ago), licensed MIT. It adds 35 tokens to every session and 253 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories