dotclaude CLAUDE.md

A set of project principles based on outcome-driven planning: define the desired end state, identify the gap, and work backward to the smallest useful path.

In plain words
What is it for?
Use it to plan features, fixes, investigations, and reviews, including deciding what tests and evidence are needed before calling work complete.
Why use it?
It helps agents stay focused on the result, state assumptions and unknowns, and verify that completed work actually meets its goal.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/thkt/dotclaude/claude-md
Clone the repo
git clone --depth 1 https://github.com/thkt/dotclaude
Per session 324 This file is loaded in full into every session.
When invoked 324 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00324 $0.00324
Opus 5 $0.00162 $0.00162
Sonnet 5 $0.00065 $0.00065
Haiku 4.5 $0.00032 $0.00032

Measured 2d ago against content hash 5adb10809364, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dotclaude 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 2d 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.md · 37 lines

What it actually says

CLAUDE.md

Foundation

Outcome-driven

An outcome is a state of being: how human users, AI agents, or the system behave when this project is in its done condition. Time, error rate, and value are indicators that corroborate the outcome.

Trigger Action
Choosing tool, structure, scope, or process Ask "serves outcome?" before "is correct?"
Work productive but outcome not closer Stop and re-derive

Backcasting

Once an outcome is set, derive the minimal path by working backward from the ideal end state.

  1. Goal. What does "done" look like in terms of outcome?
  2. Gap. What separates the current state from that goal?
  3. Path. What is the minimum set of steps from gap to goal?

Rules

Rule Directive
Response Conclusion first. Recommend first. Declare then act. Seek decisions concisely
Verify Facts cite source. Assumptions state basis. Unknowns name verification path

Completion

Task type Required Insufficient
Feature New tests added Existing tests pass alone
Fix Root cause resolved Symptom patches
Investigation How the path behaves without the bug Bug identified only
No change Show goal completion evidence and confirm with user Self-judgment alone
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. 2d ago First seen · 37 lines · 324 tokens per session scan A 5adb10809364

Subscribe to this mod's changes

dotclaude CLAUDE.md is an instructions file published in the GitHub repository thkt/dotclaude (11 stars, last pushed 3d ago), licensed MIT. It adds 324 tokens to every session, about $0.0016 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.

Related

Other instructions, from other repositories

nextclaw AGENTS.md

Instructions for Peiiii/nextclaw, covering nextclaw ai 常驻内核, 产品愿景, 沟通与推进, 深思与目标模式 and 协作与 git 安全.

Peiiii/nextclaw · 3,095 tokens

dotskills AGENTS.md

Instructions for vincentkoc/dotskills, covering agents.md, repository purpose, mandatory contribution flow, skill standards and openai metadata defaults.

vincentkoc/dotskills · 892 tokens

FMT-exocortex-template CLAUDE.md

Claude Code instructions for TserenTserenov/FMT-exocortex-template, covering инструкции для всех репозиториев, 1. архитектура репозиториев, 2. орз-фрактал (открытие → работа → закрытие), блокирующие правила and протокол работы (полный → memory/protocol-work.md).

TserenTserenov/FMT-exocortex-template · 4,800 tokens

asap-protocol AGENTS.md

AGENTS.md instructions for asap-protocol/asap-protocol, covering agents.md, project context, quick start, agent guidance (rules vs skills) and knowledge map.

asap-protocol/asap-protocol · 1,995 tokens

slipway AGENTS.md

Instructions for signalridge/slipway, covering slipway agent principles, user owns the process, investigate before clarifying, report, do not certify and maintain the whole surface.

signalridge/slipway · 470 tokens

ai-workflows AGENTS.md

Instructions for dryvist/ai-workflows, covering ai-workflows, architecture, directory structure, workflow types and consumer repo caller pattern.

dryvist/ai-workflows · 1,766 tokens