trigger_tree CLAUDE.md

A routing guide for the Trigger Tree repository. It points agents to the right documentation based on whether they are working on behavior, privacy, configuration, reports, tests, or other areas.

In plain words
What is it for?
Finding documentation for product terms, instruction checks, telemetry, dashboards, hooks, privacy, development, releases, and documentation structure.
Why use it?
It keeps agents from reading unrelated files and helps them find the rules needed for a particular change.

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/hedde/trigger_tree/claude-md
Clone the repo
git clone --depth 1 https://github.com/Hedde/trigger_tree
Per session 214 This file is loaded in full into every session.
When invoked 214 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 $0.00214 $0.00214
Opus 5 $0.00107 $0.00107
Sonnet 5 $0.00043 $0.00043
Haiku 4.5 $0.00021 $0.00021

Measured 2d ago against content hash 957c071c528a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

trigger_tree 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 · 17 lines

What it actually says

trigger-tree repository guidance

Keep this file as a router. Read only the references needed for the task.

Task Start here
Product behavior or terminology docs/README.md, then docs/glossary.md
Instruction adherence, directives, or probes docs/instruction-adherence.md
Telemetry, heat, health, or limitations docs/heat-model.md
TUI or HTML report docs/dashboard.md
Hook/config changes docs/configuration.md and docs/platform-support.md
Privacy-sensitive changes docs/privacy.md and PRIVACY.md
Tests, CI, or release work docs/development.md and CONTRIBUTING.md
Documentation structure docs/structuring-docs.md

Before shipping, run the full checks in docs/development.md. Preserve stdlib-only runtime code, local-only telemetry, explicit uncertainty, and 100% test coverage.

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 · 17 lines · 214 tokens per session scan A 957c071c528a

Subscribe to this mod's changes

trigger_tree CLAUDE.md is an instructions file published in the GitHub repository Hedde/trigger_tree (14 stars, last pushed 8d ago), licensed MIT. It adds 214 tokens to every session, about $0.0011 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.