calibrate

calibrate is a skill for Claude Code from mishahanin/heading-os. It costs 101 tokens per session (3,823 once invoked), scanned A, original, Apache-2.0.

A session-review tool that examines a Claude Code conversation for mistakes, preferences, repeated patterns, and style problems, then suggests numbered changes to project memory and settings.

In plain words
What is it for?
Use it at the end of a session to review what went well or poorly, approve suggested updates, and record them in one Git commit.
Why use it?
It helps turn lessons from one coding session into concrete improvements for future sessions while keeping company files out of automatic changes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/calibrate.py > /tmp/calibrate-envelope.json.

Good fit Use it at the end of a session to review what went well or poorly, approve suggested updates, and record them in one Git commit.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/mishahanin/heading-os
agentmods
npx agentmods add skills/mishahanin/heading-os/calibrate

Made for: Claude Code.

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/mishahanin/heading-os/calibrate/github.svg)](https://agentmods.dev/skills/mishahanin/heading-os/calibrate)
Your own site
<a href="https://agentmods.dev/skills/mishahanin/heading-os/calibrate"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/calibrate/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.

agentmods 80×15 button for calibrate

Your own site · 80×15
<a href="https://agentmods.dev/skills/mishahanin/heading-os/calibrate"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/calibrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,823 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 77
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 251
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Agent Snooping · line 254
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Excessive Agency · line 15
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
How audits are shown
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 $0.00101 $0.03823
Opus 5 $0.00051 $0.01912
Sonnet 5 $0.00020 $0.00765
Haiku 4.5 $0.00010 $0.00382

Measured 6d ago against content hash 288e5f79f116, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 6d 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.

.claude/skills/calibrate/SKILL.md · 368 lines

How it starts

The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/calibrate - End-of-Session Self-Improvement

Scans the current session for friction and successes. Proposes numbered patches grouped by target (Memory / Settings / Skills / Rules), applies approved patches, and makes a single atomic git commit. Corporate files route to a separate review queue, never auto-applied.

Design spec: docs/superpowers/specs/2026-05-13-calibrate-skill-design.md (data overlay: .heading-os-data/docs/superpowers/specs/2026-05-13-calibrate-skill-design.md). Detection prompts: references/detection-prompts.md.

Memory store

Memory patches target the canonical auto-memory store in the DATA overlay, the same store /dream, /memory-hygiene and the memory index read. Resolve it:

python3 -c "from scripts.utils.workspace import get_auto_memory_dir; print(get_auto_memory_dir())"

Do NOT write to the native harness store at ~/.claude/projects/<project-slug>/memory/. That store is a per-launch runtime cache, keyed to the directory the session started in. A patch written there is invisible to a session that launched from any other path. The SessionStart hook .claude/hooks/memory-reconcile.py bridges the two stores. It syncs both directions, newest-wins, and never deletes, so the patch is not lost. It does not reach the canonical store or the memory index until the next session starts.

Phase 0 - Pre-flight + mode dispatch

Run these checks before any other work. Each failure has a specific recovery message; never abort silently.

  1. Git available + in repo. Run git rev-parse --is-inside-work-tree. If exit != 0: abort with "git not available or not in a repo. /calibrate cannot safely auto-commit."

  2. Working tree state. Run git status --porcelain. The typical transient set is outputs/, crm/aggregated/, .sessions/ and datastore/operations/tribe/fireside-state/. If any modified file sits outside it, warn: "Working tree has uncommitted changes that aren't typical transients. Step 5.1 may collide with them, and a failed Edit aborts the run. Proceed? (proceed / cancel)". Wait for explicit answer. Record the list: a file already dirty here is NOT this run's work and is never staged in Step 5.4.

Read the full file on GitHub · 368 lines

Files

What ships with it

5 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. 6d ago Changed · +57 lines 288e5f79f116
  2. 9d ago First seen · 311 lines · 101 tokens per session scan A e0303652150f

Subscribe to this mod's changes

calibrate is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 101 tokens to every session and 3,823 once invoked, about $0.0005 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 2026-08-30.