budget SKILL.md skillA

budget from geekfamilycorp/tricorderkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add geekfamilycorp/tricorderkit/budget@v2.0

Pins v2.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
geekfamilycorp/tricorderkit
Path
cowork-plugins/tk-token-economy/skills/budget/SKILL.md
Versions recorded
1
Latest version
v2.0, committed Oct 28, 2026
Size
5,384 bytes
Repository stars
32
License
MIT

Suit, analyse et optimise la consommation mensuelle de tokens ESTIMÉE par famille de modèle (fast / default / deep, voir models.json) à partir d'un fichier local. Trois modes : `status` (consommation et seuils 50/80/95 %), `analyze` (tendance, projection fin de mois, gaspillages), `optimize` (drapeaux sûrs et réversibles, jamais appliqués sans GO explicite). À utiliser quand l'utilisateur demande « combien j'ai consommé », « budget tokens », « où partent mes tokens », « projection budget », «…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Budget (status · analyze · optimize)

Un seul fichier de données : `~/.tk-token-economy/budget.json` (schéma v1.1, archivé chaque mois dans `~/.tk-token-economy/history/`). Trois scripts, trois modes.

**Honnêteté des chiffres** : tout est estimé (poids d'équivalence fast 1/1, default 3/5, deep 15/25 pour input/output). Comparer à l'usage réel et corriger via `--calibration` avant de trancher un arbitrage.

## Alimentation des données

1. **Automatique** — hook `PostToolUse` sur `Task` (`hooks/hooks.json`) → `budget.py log-from-task`. Il ne logge que si le payload contient des compteurs de tokens ; **en Cowork ce n'est pas toujours le cas** : un statut à 0 ne veut pas dire zéro consommation.
2. **Manuel (repli)** — après une exécution significative :

```bash
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/budget.py log --model default --in 3200 --out 1800
```

`--model` accepte les alias `fast` / `default` / `deep` (ou la famille). Les tokens se lisent dans le résumé d'usage de la session ou s'estiment avec `classify.py`.

## Mode `status`

```bash
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/budget.py status          # lisible
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add geekfamilycorp/tricorderkit/budget@sha256:92a32b253ae5dad6

The line at the top of this page pins the label v2.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_e7itaa7gotqpy7qf.svg)](https://markdownregistry.com/a/art_e7itaa7gotqpy7qf)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 28, 2026.

versioncommittedcommitsizeaudit
v2.0 latest2026-10-28 8d1d6ce 5,384 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5384 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

geekfamilycorp/tricorderkit · 32 stars · license MIT · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_e7itaa7gotqpy7qf
GET https://markdownregistry.com/api/v1/resolve?ref=geekfamilycorp/tricorderkit/budget
GET https://markdownregistry.com/api/v1/blob/92a32b253ae5dad624d55c85c8b046edf46858eb5de0806173032d8451a4f514

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from geekfamilycorp/tricorderkit

open-source-jp-scraper SKILL.md skill
geekfamilycorp/tricorderkit · .claude/skills/open-source-jp-scraper/SKILL.md
git:20261028.8d1d6ce · audit C · 32 stars
vault-token-optimizer SKILL.md skill
geekfamilycorp/tricorderkit · .claude/skills/vault-token-optimizer/SKILL.md · Optimize any Markdown or Obsidian vault for Claude Code by analyzing structure first, generating manifests, routing…
git:20261028.8d1d6ce · audit A · 32 stars
AGENTS.md AGENTS.md file
geekfamilycorp/tricorderkit · AGENTS.md
git:20261028.8d1d6ce · audit A · 32 stars
CLAUDE.md CLAUDE.md file
geekfamilycorp/tricorderkit · CLAUDE.md
git:20261028.8d1d6ce · audit A · 32 stars
agent-config-audit SKILL.md skill
geekfamilycorp/tricorderkit · cowork-plugins/tk-agent-security/skills/agent-config-audit/SKILL.md · Audit de sécurité en lecture seule de la CONFIGURATION DE L'AGENT lui-même (pas de l'application) — serveurs MCP et…
v1.1 · audit B · 32 stars
cli-compress SKILL.md skill
geekfamilycorp/tricorderkit · cowork-plugins/tk-agent-security/skills/cli-compress/SKILL.md · Compresse les sorties de commandes shell verbeuses (git, npm, docker, kubectl, pytest, cargo…) avant qu'elles n'entrent…
v2.0 · audit B · 32 stars
graphrag-hybrid SKILL.md skill
geekfamilycorp/tricorderkit · cowork-plugins/tk-data-ops/skills/graphrag-hybrid/SKILL.md · Répond à une question par recherche hybride locale : similarité vectorielle dans Qdrant, puis expansion du voisinage…
v0.1.0 · audit A · 32 stars
neo4j-graph-ops SKILL.md skill
geekfamilycorp/tricorderkit · cowork-plugins/tk-data-ops/skills/neo4j-graph-ops/SKILL.md · Interroge et fait évoluer le graphe de connaissances Neo4j d'une stack locale (APOC/GDS) via le serveur MCP officiel…
v0.1.0 · audit A · 32 stars
scrape-adaptive SKILL.md skill
geekfamilycorp/tricorderkit · cowork-plugins/tk-data-ops/skills/scrape-adaptive/SKILL.md · Collecte des pages web de façon robuste et respectueuse avec Scrapling (BSD-3 : parseur adaptatif qui retrouve un…
v0.1.0 · audit A · 32 stars
watch-changes SKILL.md skill
geekfamilycorp/tricorderkit · cowork-plugins/tk-data-ops/skills/watch-changes/SKILL.md · Met en place et exploite une veille de changements de pages et de flux, en local : changedetection.io (Apache-2.0…
v0.1.0 · audit A · 32 stars
code-corrector SKILL.md skill
geekfamilycorp/tricorderkit · cowork-plugins/tk-dev-discipline/skills/code-corrector/SKILL.md · Corrige et durcit le code d'une application web de façon disciplinée et mesurée. À utiliser quand l'utilisateur veut…
v1.1 · audit A · 32 stars
debugging-and-error-recovery SKILL.md skill
geekfamilycorp/tricorderkit · cowork-plugins/tk-dev-discipline/skills/debugging-and-error-recovery/SKILL.md · Débogage discipliné par cause racine pour scripts Python, VPS (systemd/Docker/SFTP), pipelines de veille et…
v1.1 · audit A · 32 stars

Every file in geekfamilycorp/tricorderkit

Other files named budget

budget SKILL.md skill
marcel-bich/marcel-bich-claude-marketplace · plugins/credo/skills/budget/SKILL.md · The single source for all API budget cap and reset rules - how much of the 5-hour and weekly API limits may be spent…
git:20261101.1d88c1c · audit B · 12 stars

Browse by kind, by grade A, or by owner.