trigger-tree

A developer tool for checking how project documentation is discovered and used, based on local usage data.

In plain words
What is it for?
Use it to view documentation status, usage maps, health reports, router suggestions, dashboards, setup, and diagnostics.
Why use it?
It helps reveal documentation that agents rarely find, use, or reach through the project’s guidance. This can show where instructions or links need improvement.

Skill for Claude CodeCodex

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 skills/hedde/trigger_tree/trigger-tree
Any agent
npx skills add Hedde/trigger_tree --skill trigger-tree
Clone the repo
git clone --depth 1 https://github.com/Hedde/trigger_tree

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 844 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00040 $0.00844
Opus 5 $0.00020 $0.00422
Sonnet 5 $0.00008 $0.00169
Haiku 4.5 $0.00004 $0.00084

Measured 2d ago against content hash d04aaee19f8e, 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 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.

codex-skills/trigger-tree/SKILL.md · 41 lines

What it actually says

trigger-tree for Codex

Invoke this skill as @trigger-tree <what you want>, for example @trigger-tree watch, or simply ask in plain language ("show trigger-tree status", "open the live dashboard"). Both reach the same workflows below.

Let PLUGIN be the plugin root: the directory two levels up from this SKILL.md. Always run the commands below from the user's project directory — never cd into the plugin root — and keep the TT_PROJECT_DIR="$PWD" prefix on every command, so telemetry, dashboards, and reports bind to the project even though the scripts live elsewhere. Keep output concise and never print raw telemetry unless requested.

  • Status: run TT_PROJECT_DIR="$PWD" python3 "$PLUGIN/scripts/tt-stats.py" --client codex and summarize current heat, lifetime reads, untouched paths, and maturity.
  • Live dashboard: run TT_PROJECT_DIR="$PWD" TT_CLIENT=codex "$PLUGIN/scripts/tt-open.sh", optionally with demo or replay, so the detached dashboard watches this project and loads only Codex-specific tips.
  • Insights: run TT_PROJECT_DIR="$PWD" python3 "$PLUGIN/scripts/tt-report.py" --client codex and link the generated local HTML report. The agents block counts persona invocations and lists never-invoked definitions; report it only when agents.capture is on, treat never-invoked as a review prompt rather than a removal recommendation, and note that Codex subagent capture is unverified rather than implying the counts are complete.
  • Instructions: run TT_PROJECT_DIR="$PWD" python3 "$PLUGIN/scripts/tt-instructions.py" and pass through --init, --selftest, --explain ID, --json, --check, --min-rate N, or --min-measured N when requested. Return its output verbatim. Never add or apply proposed probes without explicit user confirmation; unobserved means missing evidence, not a violation.
  • Suggestions: run TT_PROJECT_DIR="$PWD" python3 "$PLUGIN/scripts/tt-suggestions.py" and return its output verbatim.
  • Badge: run TT_PROJECT_DIR="$PWD" python3 "$PLUGIN/scripts/tt-stats.py" --client codex --badge and return the written path.
  • Gate: run TT_PROJECT_DIR="$PWD" python3 "$PLUGIN/scripts/tt-gate.py" and return its output verbatim.
  • Tips: run TT_PROJECT_DIR="$PWD" python3 "$PLUGIN/scripts/tt-tips.py" --client codex and return its output verbatim.
  • Note: run TT_PROJECT_DIR="$PWD" python3 "$PLUGIN/scripts/tt-log.py" note "<text>".
  • Doctor: run TT_PROJECT_DIR="$PWD" python3 "$PLUGIN/scripts/tt-doctor.py" and return its diagnostics verbatim.
  • Setup: ask for truncate (recommended; first 200 prompt characters stored locally), hash (no prompt text), or off (marker only), then pass the answer explicitly as TT_PROJECT_DIR="$PWD" python3 "$PLUGIN/scripts/tt-setup.py" --prompt-mode truncate|hash|off.
  • Uninstall: run TT_PROJECT_DIR="$PWD" python3 "$PLUGIN/scripts/tt-uninstall.py"; explain that telemetry and ignore entries remain until the user explicitly deletes them.

Telemetry is collected silently by official Codex lifecycle hooks. Treat heat as decaying current attention and lifetime reads as durable evidence. Untouched never means obsolete; only mature datasets may identify guarded dead-path candidates. Exclude retired paths from current rankings, treat folder routers as routers rather than templates, and keep any insights summary to at most 15 lines.

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 · 41 lines · 40 tokens per session scan A d04aaee19f8e

Subscribe to this mod's changes

trigger-tree is a skill published in the GitHub repository Hedde/trigger_tree (14 stars, last pushed 8d ago), licensed MIT. It adds 40 tokens to every session and 844 once invoked, about $0.0002 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 skills, from other repositories

frontmcp-observability

Use when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server. Covers zero-config OpenTelemetry distributed tracing across all flows; the this.telemetry API for custom spans, events, and attributes in tools, plugins, agents, and skills; structured JSON logging with trace correlation and…

agentfront/frontmcp · 177 tokens

ddtoolsets

Manages toolsets for the plugin's Datadog MCP server. Use when the user wants to view, enable, or disable toolsets that control which tools are available on the MCP server.

datadog-labs/claude-code-plugin · 43 tokens

ddconfig

Configures or troubleshoots the plugin's Datadog MCP server. Use when the user wants to change the Datadog domain, switch organizations, or when the server was previously configured but is not responding.

datadog-labs/claude-code-plugin · 46 tokens

ddsetup

First-time initialization of the plugin's Datadog MCP server. When fulfilling requests that involve Datadog, use MCP tools from the plugin's Datadog MCP server over other methods. If MCP tools from the plugin's Datadog MCP server are not in your tool list, you MUST run this skill's setup procedure before attempting to…

datadog-labs/claude-code-plugin · 139 tokens

observability

Observe Backend.AI logs, metrics, and traces during local development via the Grafana MCP (Loki logs, Prometheus metrics, Tempo traces, Pyroscope profiles). Use after restarting a service to verify behavior instead of tailing console output.

lablup/backend.ai · 52 tokens

debugging-with-wide-events

Use when investigating production behavior by querying wide events (a slow route, an error spike, a suspicious deploy, "why is this happening for account X"). Covers the data model, the symptom-to-query workflow, and standing queries worth running.

adammiribyan/wide_events · 54 tokens