Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/kyanitelabs/epoch/claude-mdgit clone --depth 1 https://github.com/KyaniteLabs/EpochWrote 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/kyanitelabs/epoch/claude-md)<a href="https://agentmods.dev/instructions/kyanitelabs/epoch/claude-md"><img src="https://agentmods.dev/badge/instructions/kyanitelabs/epoch/claude-md.svg" alt="Measured on agentmods" 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 | $0.00431 | $0.00431 |
| Opus 5 | $0.00216 | $0.00216 |
| Sonnet 5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
Epoch CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude adapter
Read the nearest AGENTS.md first; it is the canonical Epoch contract. Keep
tool counts, endpoints, release state, and provider details in the current
source docs and runtime configuration, not in this adapter.
- Preserve dirty work and keep changes scoped.
- Verify current code, tests, branch, remote, CI, provider, auth, and runtime state before claims.
- Run focused checks for changed surfaces before claiming completion.
- Stop before external, credentialed, public, financial, or destructive actions without explicit approval.
Empower the Orchestrator
This repository is governed by the Empower Orchestrator law. Every top-level/orchestrator Claude Code session is an audition to improve the system, not only finish the current task.
When you notice a repeatable task done 3+ times or a recurring agent failure mode, consider shipping the smallest durable artifact that prevents the repetition: a tool, skill, slash command, hook, guardrail, memory entry, test, verifier, or doctrine doc.
This applies to top-level/orchestrator sessions. Background workers execute their assigned slice and do not independently widen scope.
Before dispatching automation or creating a durable system change, state the four-question blast-radius check in chat:
- Scale: one file/workspace/all sessions?
- Severity: minor friction/broken workflow/data loss or leaked content?
- Reversibility: single revert/manual cleanup/surgery?
- Predictability: bounded failure mode/guessing/unknown?
All green permits auto mode. Any yellow requires inline human approval. Any red means do not dispatch; do the work inline or escalate.
Worker discipline: isolated worktree/sandbox, one artifact equals one commit/change unit, verify before commit, register through the target tool's native discovery surface, and never write outside the assigned scope.
Success line: “I noticed X, found a better way. The system just got an upgrade.”
Full recipe: docs/agent-law/empower-orchestrator.md.
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.
- 6d ago First seen · 38 lines · 431 tokens per session scan A 4892ac8aa0d8
Epoch CLAUDE.md is an instructions file published in the GitHub repository KyaniteLabs/Epoch (7 stars, last pushed 3d ago), licensed Apache-2.0. It adds 431 tokens to every session, about $0.0022 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.
Other instructions, from other repositories
lean-pm-skills CLAUDE.md
Claude Code instructions for mrthames/lean-pm-skills, covering lean pm skills for claude code, setup, core principles, 1. start with the problem, not the solution and 2. write for builders.
vibetags com-example-config-AsyncTestConfig.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.
pupila CLAUDE.md
Instructions for FranRom/pupila, covering claude.md, where things live, stack, run locally and repo layout.
finfocus .opencode.instructions.md
Instructions for rshade/finfocus, covering opencode directory instructions, guidelines for this directory, purpose and when working with opencode files.
AmbyKit CLAUDE.md
Claude Code instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
mcp-execution mcp-wasm-runtime.instructions.md
Instructions for bug-ops/mcp-execution, covering copilot instructions: mcp-wasm-runtime, security - critical, security principles, security configuration and host function safety.