Borrowing it
Nothing to install: this file belongs to odere-pro/claude-calibration. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/odere-pro/claude-calibration/main/CLAUDE.mdgit clone --depth 1 https://github.com/odere-pro/claude-calibrationWrote 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.
[](https://agentmods.dev/instructions/odere-pro/claude-calibration/claude-md)<a href="https://agentmods.dev/instructions/odere-pro/claude-calibration/claude-md"><img src="https://agentmods.dev/badge/instructions/odere-pro/claude-calibration/claude-md/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.
<a href="https://agentmods.dev/instructions/odere-pro/claude-calibration/claude-md"><img src="https://agentmods.dev/badge/instructions/odere-pro/claude-calibration/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02887 | $0.02887 |
| Opus 5 | $0.01443 | $0.01443 |
| Sonnet 5 | $0.00577 | $0.00577 |
| Haiku 4.5 | $0.00289 | $0.00289 |
Grade A, and why
claude-calibration CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| G12 `12-hooks-no-remote` | no `curl`/`wget`/remote `npx` in hooks | network on the hot path | How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-calibration — plugin development
This repo is the source for the claude-calibration Claude Code plugin. It is not an
application — every file under here ships to end users when the plugin is installed.
What ships
.claude-plugin/plugin.json— manifest (version of record)
This repo no longer ships its own marketplace.json. Distribution is via the external
odere-pro aggregator marketplace,
which lists this plugin by github source — install with claude-calibration@odere-pro.
skills/calibrate*/— orchestrators + 9 per-feature bundlesskills/calibration-*/— top-level flows:calibration(dispatcher),calibration-audit,calibration-diff,calibration-track,calibration-flow,calibration-doctor,calibration-onboardingworkflows/calibration-audit-parallel.mjs— aWorkflowscript (run via theWorkflowtool //workflows) that parallelizes the read-only audit: it fans the 9 feature evaluators out via a deterministicparallel()overcalibration-feature-evaluator, then synthesizes viacalibration-evaluator. There is no native plugin component for workflows, so the SessionStart hookinstall-workflows.shcopies it into the project's.claude/workflows/registry on session start (idempotent, never clobbers local edits); same reports as/claude-calibration:calibration-auditagents/calibration-*.md— 5 worker subagents: planner, evaluator, calibrator,calibration-feature-evaluator(haiku worker the evaluator fans out to in parallel), andcalibration-flow-evaluator(sonnet worker the/calibration-flowbehavioural flow spawns)rules/{signatures,dispatch}.md— canonical signature catalogue + dispatch maphooks/{hooks.json,calibrator-write-guard.sh,audit-write-guard.sh}—PreToolUsewrite-guardshooks/install-workflows.sh—SessionStarthook that installsworkflows/*.mjsinto the project's.claude/workflows/docs/— human-readable rubric (the doc-set the plugin grades against)
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.
- 8d ago First seen · 164 lines · 2,887 tokens per session scan A 6d8f7532365e
claude-calibration CLAUDE.md is an instructions file published in the GitHub repository odere-pro/claude-calibration (1 stars, last pushed 1mo ago), licensed MIT. It adds 2,887 tokens to every session, about $0.0144 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.