calibrate

calibrate is a skill for Claude Code from pitimon/8-habit-ai-dev. It costs 89 tokens per session (1,831 once invoked), scanned A, original, MIT.

A short self-assessment that determines how much development guidance a person needs and saves that preference for later sessions.

In plain words
What is it for?
Use it to set a guidance level for coding-agent support, from detailed instruction to brief checkpoints and team-focused prompts.
Why use it?
It avoids giving every developer the same level of explanation, whether they are new to the work or highly experienced.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the 8-habit-ai-dev plugin — 24 skills, 2 agents, 1 hook shipped together

Good fit Use it to set a guidance level for coding-agent support, from detailed instruction to brief checkpoints and team-focused prompts.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add pitimon/8-habit-ai-dev
Claude Code
/plugin install 8-habit-ai-dev

Made for: Claude Code.

Or install 8-habit-ai-dev, the plugin that ships this one along with the rest of its 24 skills, 2 agents, 1 hook.

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 calibrate

README.md
[![agentmods](https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/calibrate.svg)](https://agentmods.dev/skills/pitimon/8-habit-ai-dev/calibrate)
Your own site
<a href="https://agentmods.dev/skills/pitimon/8-habit-ai-dev/calibrate"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/calibrate.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,831 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00089 $0.01831
Opus 5 $0.00044 $0.00915
Sonnet 5 $0.00018 $0.00366
Haiku 4.5 $0.00009 $0.00183

Measured 8d ago against content hash 9aadbd9b2dc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

calibrate 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 8d 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.

plugin/skills/calibrate/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Calibrate (ปรับจูนระดับวุฒิภาวะ)

Habit: H8 — Find Your Voice | Anti-pattern: Giving identical verbose guidance to a senior engineer and a first-time user

Why This Exists

The maturity model defined in rules/effective-development.md — Dependence → Independence → Interdependence → Significance — has existed in this plugin's rules for a long time but was never operationalized. Every session treated experienced users the same as first-run users: same verbose prompts, same checkpoint ceremony, same beginner examples. This wastes experienced users' tokens and time, and reads as condescending.

/calibrate closes that gap. It runs a brief self-assessment, writes a profile file, and lets other skills adapt. No enforcement, no tracking — just a signal the user opts into that informs the guidance they receive.

Inspired by (not copied from) Hermes Agent's USER.md pattern: explicit, user-facing, and editable. We do not implement passive inference (that would need a runtime we don't have) — this is active self-assessment instead.

Process

Step 0: Check for an existing profile

Read ~/.claude/habit-profile.md. Three cases:

Case A — no profile exists: proceed to Step 1 (fresh calibration).

Case B — profile exists and is less than 90 days old: show the user their current level, calibrated date, and age in days. Ask: "Your profile says you're at [Level], calibrated [N] days ago. Re-calibrate anyway?" If no, exit with the current profile path. If yes, proceed to Step 1.

Case C — profile exists and is 90+ days old: show the user their current level and age. Say: "Your profile is [N] days old — your practice may have changed. Recommend re-calibrating." Then ask the same yes/no. Default to yes at this age.

If the argument --force is present, skip the confirmation entirely and proceed to Step 1.

Step 1: Ask the 5 core questions

Ask these five questions one at a time. Wait for each answer before asking the next. Do not paste all five at once — give the user space to think.

Read the full file on GitHub · 116 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 116 lines · 89 tokens per session scan A 9aadbd9b2dc5

Subscribe to this mod's changes

calibrate is a skill published in the GitHub repository pitimon/8-habit-ai-dev (3 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,831 once invoked, about $0.0004 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

sitrep

Situational awareness — where am I, what was I doing, what's next. Context recovery after compression, confusion, or mid-session reorientation.

martineserios/thebrana · 32 tokens

caveman

Ultra-compressed mode — 65-75% fewer tokens, preserving technical accuracy. Strips filler, hedging, pleasantries. Code/commits stay in normal language.

martineserios/thebrana · 41 tokens

i-have-adhd

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

ayghri/i-have-adhd · 62 tokens

joycraft-bugfix

Structured bug fix workflow — triage, diagnose, discuss with user, write a focused spec, hand off for implementation.

maksutovic/joycraft · 29 tokens

sitrep-panel

Keep a live local HTML report updated as you work on a task — a status board, a running "what's happening now" narrative, screenshots, and a newest-first log — served on localhost so the user can watch progress in a browser tab instead of reading the transcript. Use when the user invokes /sitrep-panel, asks for a…

dbl8005/sitrep-panel · 101 tokens

git-workflow

Use when starting feature work that needs a branch, creating worktrees for isolation, making atomic commits during development, or completing a development branch via merge, PR, preserve, or discard. Also use when the user says "set up worktree", "create PR", "finish this branch", "start feature", or when you need an…

lgbarn/shipyard · 76 tokens