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/holgerleichsenring/agent-smith/claude-mdgit clone --depth 1 https://github.com/holgerleichsenring/agent-smithWrote 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/holgerleichsenring/agent-smith/claude-md)<a href="https://agentmods.dev/instructions/holgerleichsenring/agent-smith/claude-md"><img src="https://agentmods.dev/badge/instructions/holgerleichsenring/agent-smith/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 | $0.02302 | $0.02302 |
| Opus 5 | $0.01151 | $0.01151 |
| Sonnet 5 | $0.00460 | $0.00460 |
| Haiku 4.5 | $0.00230 | $0.00230 |
Grade A, and why
agent-smith 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 yesterday.
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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-smith — AI Agent Instructions
Context Files (read in this order)
- Every
.agentsmith/contexts/<name>/context.yaml(globcontexts/*/context.yaml) — architecture, stack, integrations, phase status PER stack - Every
.agentsmith/contexts/<name>/principles.md— code quality rules per stack (ALWAYS follow) .agentsmith/phases/active/*.yaml— spec for the phase being implemented (itsapplies_to:names the dominant context).agentsmith/decisions/*.yaml— past decisions, one YAML per phase or run (read the active phase's file and itsrequires:chain).agentsmith/memory/MEMORY.md— the experiential-memory index, one line per recorded fact; recall detail from.agentsmith/memory/<name>.mdon demand when a line touches your task
Phase Directory Structure
.agentsmith/phases/
done/ # completed phases (historical reference)
active/ # phase currently being worked on
planned/ # upcoming phases with requirements
Experiential Memory (remember / recall)
.agentsmith/memory/ holds typed Markdown facts: one file per memory with
frontmatter name (slug = filename), description (one line), and
metadata.type (feedback = how the operator wants the agent to work,
ratification required; project = goals/constraints/state not derivable from
code or git; reference = external pointers). MEMORY.md is the index —
one line per memory, content never in the index.
- Recall before re-deriving: when the index hints at a fact you are about to work out from scratch, read the entry file instead.
- Remember sparingly: store what code and git cannot already tell the
next agent — one fact per file; check the index for an existing entry and
update rather than duplicate; delete a memory that turns out wrong; link
related memories as
[[slug]](a cited slug requires its committed definition). A new or changedfeedbackentry is a PROPOSAL until the operator ratifies it. - Memory vs decision: a decision records a CHOICE (
decisions/); a memory records a transferable FACT or RULE. Never duplicate one into the other.
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.
- yesterday Changed · -5 tokens per session abb383ac23d7
- 6d ago First seen · 143 lines · 2,307 tokens per session scan A 8ae4727a9279
agent-smith CLAUDE.md is an instructions file published in the GitHub repository holgerleichsenring/agent-smith (23 stars, last pushed yesterday), licensed MIT. It adds 2,302 tokens to every session, about $0.0115 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.
Other instructions, from other repositories
teamxray copilot-instructions.md
Copilot instructions for AndreaGriffiths11/teamxray, covering github copilot instructions for mcp team x-ray extension, response style, build, test, and lint commands, validating extension changes and architecture.
teamxray AGENTS.md
AGENTS.md instructions for AndreaGriffiths11/teamxray, covering agents.md, purpose, tagline, tech stack and architecture.
claude-code-gauntlet AGENTS.md
AGENTS.md instructions for liatrio-labs/claude-code-gauntlet, covering agents.md, design, tooling boundary (no npm in the tree), scripts and tests.
claude-code-gauntlet CLAUDE.md
Claude Code instructions for liatrio-labs/claude-code-gauntlet, covering claude.md and claude code specifics.
baron CLAUDE.md
Claude Code instructions for loncadev/baron, covering baron — project rules, tech stack, local development, conventions and testing.
pr-comments-resolver CLAUDE.md
Instructions for Dropelikeit/pr-comments-resolver, covering pr comments resolver — development guide, project structure, plugin format, conventions and adding a new skill.