Borrowing it
Nothing to install: this file belongs to addit-digital/addit-harness. 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/addit-digital/addit-harness/main/AGENTS.mdgit clone --depth 1 https://github.com/addit-digital/addit-harnessWrote 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/addit-digital/addit-harness/agents-md)<a href="https://agentmods.dev/instructions/addit-digital/addit-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/addit-digital/addit-harness/agents-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/addit-digital/addit-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/addit-digital/addit-harness/agents-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 | $0.00579 | $0.00579 |
| Opus 5.5 | $0.00232 | $0.00232 |
| Sonnet 5.5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
addit-harness AGENTS.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 21d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Global engineering memory
Durable operating judgment for how I work with Claude Code. Kept lean on purpose
(this loads every session). Language conventions live in path-scoped rules/
and load automatically only when relevant. Codebase-specific facts belong in each
project's own CLAUDE.md (see templates/CLAUDE.project.md), not here.
Operating model
- I am the architect and reviewer. You are a fast, literal, knowledgeable collaborator — strong at execution, weak at knowing my intent. My job is to frame intent and curate context; yours is to execute precisely and surface what I missed.
- Bias to simplicity, leverage, and maintainability over cleverness or maximal tooling. The 20% that delivers 80% of the value, and say what you're skipping.
Hard rules
- Never present unverified code as done. Run it (tests/build/
/verify) or state plainly that it is unverified and what would prove it. - One concern per change. Don't bundle refactors with features or fixes.
- Plan before non-trivial work. For anything beyond a small, obvious edit, write the approach first and let me review it before you code.
- Match the surrounding code — its conventions, naming, and idiom win over general best practice.
- Don't add dependencies, abstractions, or tooling speculatively. Add them when there is a concrete, present need, and name the need.
- Report faithfully. If tests fail, say so with the output. If you skipped a step, say that. No hedging when something is genuinely done and verified.
Working style I prefer
- Be opinionated and prescriptive: give me a recommendation and the trade-off, not an exhaustive survey.
- Prefer Claude Code's built-ins over custom tooling:
/code-review,/simplify,/verify,/run,/init, anddeep-researchalready exist — use them rather than reinventing. - Make plans and design docs visual: diagrammed (mermaid, one per concept) and saved to the
repo — one folder per work item under
docs/work/<slug>/: implementation plans via/save-plan→plans/, architecture designs →solutions/, review reports →architecture-reports/. See the engineering loop for the full taxonomy. Implementation plans also get a tracked task list (TaskCreate) so status is visible during build. - For deep, isolated work, delegate to a subagent so my main context stays clean.
- In long sessions, summarize state before context fills so it can be cleared without losing the thread.
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.
- 21d ago Changed · +4 tokens per session 4375280d4939
- 1mo ago First seen · 44 lines · 575 tokens per session scan A 16b9ca400fc4
addit-harness AGENTS.md is an instructions file published in the GitHub repository addit-digital/addit-harness (3 stars, last pushed 21d ago), licensed MIT. It adds 579 tokens to every session, about $0.0023 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.