calibrate SKILL.md skillA

calibrate from akiiwa-games/agentcompass is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add akiiwa-games/agentcompass/calibrate@git:20261113.85bb5f7

Pins git:20261113.85bb5f7 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
akiiwa-games/agentcompass
Path
audit/calibrate/SKILL.md
Versions recorded
3
Latest version
git:20261113.85bb5f7, committed Nov 13, 2026
First version recorded
Nov 13, 2026
Size
6,888 bytes
Repository stars
5
License
MIT

Maintainer-only calibration loop for AgentCompass: run audit/calibration_report.py over the recorded dispatch outcomes in the state directory, read where the classifier's hours, the spend estimate or the endings deviate, and change only the shipped reference data that carries calibration. Not installed for users.

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

# Calibration Skill (`calibrate`)

Runs on the maintainer's machine only. It lives in `audit/calibrate/`, next to the report it drives, and like
`packaging/verify-release/SKILL.md` it is not one of the skills `agentcompass setup` links into hosts
(`sync_host_globals.py` links only `skills/`). Open it by path when calibrating. What it changes reaches users through
the normal channels: shipped public reference data and releases.

## Boundaries (decided, do not relax)

- Recorded outcomes never feed routing at runtime. Quota economy uses only current-period consumption and the
  allocation modules do not import the ground-truth fields. The report proposes nothing and writes no routing input; you
  read it and edit by hand.
- Model category scores come only from public cited boards or maintainer manual scores. A local sample never becomes a
  model score, and a deviation in one model's hours or spend is not evidence about its category scores.
- Tests never pin a routing outcome (`AGENTS.md`, "Routing Tests Assert Rules, Never Outcomes"). A deviation is a reason to
  revisit a rule, a formula or a parameter, never to assert a winner.
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_foeklnjjqpb242kx/ef7bbf88d1fc88a85a3549b1c475d55c46aa4a2141a763eb9cb87a41b3126ae0.json

Then /plugin install calibrate@markdownregistry-foeklnjjqpb242kx in Claude Code. It installs git:20261113.85bb5f7, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add akiiwa-games/agentcompass/calibrate@sha256:ef7bbf88d1fc88a8

The line at the top of this page pins the label git:20261113.85bb5f7, 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_foeklnjjqpb242kx.svg)](https://markdownregistry.com/a/art_foeklnjjqpb242kx)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in akiiwa-games/agentcompass/calibrate since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of calibrate from somewhere else? Ask it: where did my calibrate come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 3 versions of this file, all committed on Nov 13, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261113.85bb5f7 latest2026-11-13 85bb5f7 6,888 BA view · diff
git:20261113.a6b9b5b2026-11-13 a6b9b5b 6,273 BA view · diff
git:20261113.25d01082026-11-13 25d0108 5,321 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

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 (6888 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

akiiwa-games/agentcompass · 5 stars · license MIT · pushed 2026-11-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_foeklnjjqpb242kx
GET https://markdownregistry.com/api/v1/resolve?ref=akiiwa-games/agentcompass/calibrate
GET https://markdownregistry.com/api/v1/blob/ef7bbf88d1fc88a85a3549b1c475d55c46aa4a2141a763eb9cb87a41b3126ae0

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 akiiwa-games/agentcompass

AGENTS.md AGENTS.md file
akiiwa-games/agentcompass · AGENTS.md
git:20261113.407d2fb · audit A · 5 stars
CLAUDE.md CLAUDE.md file
akiiwa-games/agentcompass · CLAUDE.md
git:20261112.c81b215 · audit B · 5 stars
llms.txt llms.txt file
akiiwa-games/agentcompass · llms.txt
git:20261113.4d7b5b7 · audit A · 5 stars
verify-release SKILL.md skill
akiiwa-games/agentcompass · packaging/verify-release/SKILL.md · Pre-release behavioral verification for AgentCompass (router + tray) and usage-float. Installs from the built release…
git:20261112.1c7cc33 · audit A · 5 stars
agent-compass SKILL.md skill
akiiwa-games/agentcompass · skills/agent-compass/SKILL.md · Choose owner, model and effort, outbound authorization, advisor use, and continuation for delegated work. Reads local…
git:20261117.b6f84e1 · audit A · 5 stars
chatgpt-pro-consult SKILL.md skill
akiiwa-games/agentcompass · skills/chatgpt-pro-consult/SKILL.md · Carry out a agent-compass-authorized Pro consultation or plan critique through the isolated codex-chatgpt-web…
git:20261113.608da84 · audit A · 5 stars
dot-subagent SKILL.md skill
akiiwa-games/agentcompass · skills/dot-subagent/SKILL.md · Leaf-only runner for the local OpenAI Dot through dot2api. Use only after agent-compass has chosen Dot. Covers the…
git:20261030.a89d697 · audit A · 5 stars
gemini-web SKILL.md skill
akiiwa-games/agentcompass · skills/gemini-web/SKILL.md · Run Gemini web work through AgentCompass's signed-in Gemini Web Chrome (CDP 127.0.0.1:17849), including Gemini Omni 1.1…
git:20261030.a89d697 · audit A · 5 stars

Every file in akiiwa-games/agentcompass

Other files named calibrate

calibrate SKILL.md skill
wellwelwel/lagune · .claude/skills/calibrate/SKILL.md · Confronts every block, warning, and piece of noise a change raises with the false positives real projects trigger…
git:20261114.380681d · audit A · 221 stars
calibrate SKILL.md skill
apache/magpie · plugins/magpie-contributor-growth/skills/calibrate/SKILL.md · Derive committer and <governance-body> reference levels from the project's own past nomination decisions on…
git:20261118.4e96aba · audit A · 151 stars
calibrate SKILL.md skill
grainulation/grainulator · skills/calibrate/SKILL.md · Score past predictions against actual outcomes. Closes the feedback loop.
git:20260922.e702f49 · audit A · 86 stars
calibrate SKILL.md skill
borda/ai-rig · plugins/codex-rig/skills/calibrate/SKILL.md · Calibrate skills/role cards for leaks/gaps with recall, precision, and confidence-accuracy checks.
git:20261031.2278c0c · audit A · 31 stars
calibrate SKILL.md skill
borda/ai-rig · plugins/cc_foundry/skills/calibrate/SKILL.md · Calibration testing for agents and skills. Generates synthetic problems with known outcomes (quasi-ground-truth), runs…
git:20261102.52ad0cc · audit A · 31 stars
calibrate SKILL.md skill
holobiomicslab/asb-skill-collections · tests/fixtures/advertised_counts/matching/collections/astronomy/v1/leaves/calibrate/SKILL.md · Use when calibrating one astronomy instrument.
git:20260913.953db02 · audit B · 16 stars
calibrate SKILL.md skill
holobiomicslab/asb-skill-collections · tests/fixtures/advertised_counts/stale/collections/astronomy/v1/leaves/calibrate/SKILL.md · Use when calibrating one astronomy instrument.
git:20260913.953db02 · audit B · 16 stars
calibrate SKILL.md skill
skymanbp/sci-paper · skills/calibrate/SKILL.md · Make the plugin yours. Walks the whole calibration chain for one field — corpus intake, profile extraction, per-axis…
git:20261103.6a36adf · audit A · 6 stars

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