· 1 observation
Technical updates · 1
Package or technical metadata updated
View technical comparison →Hedde van der Heide v1.30.2
See which docs your AI reads
From the developer
Not specified in the available declarations: limitations, pricing & account requirements.
Show trigger-tree status for this repository.
Developer declarations; not independently tested. Listing last checked Nov 5, 2026. Package observed Nov 5, 2026.
From the marketplace listing
Local, zero-token documentation telemetry with a live dashboard, decaying heat maps, health diagnostics, and evidence-backed router fixes.
Language: English · Automatically detected from descriptions.
Exact text from the indicated source. A mention alone does not establish support for your task.
Local, zero-token documentation discovery telemetry for Codex and Claude Code.
documentation telemetry observability docs-as-code codex
· 1 observation
Package or technical metadata updated
View technical comparison →· 2 observations
Package or technical metadata updated
View technical comparison →· 2 observations
Package or technical metadata updated
View technical comparison →Package or technical metadata updated
View technical comparison →Find competitors to follow as you develop your plugin.
Find reviewed Glow public research documentation, read a cited example laboratory report, and compare a lot label with the report’s lot i...
Shared terms: document, read, documentation, evidence
Tailor lets ChatGPT read Tailor Platform's public documentation and answer questions about building on it, grounded in the published docs...
Shared terms: document, documentation, token, code
Write, lint and document APIs with Redocly. Skills for Redocly CLI, lint rules and Redocly docs projects, plus live search across the Red...
Shared terms: document, documentation, live
ReadMe MCP server packaged as a plugin. Search, read, and update your ReadMe docs and API reference from your editor.
Shared terms: document, documentation, read
LLMs rely on outdated or generic information about the libraries you use. You get outdated code examples based on year-old training data ...
Shared terms: document, documentation, code
---
name: trigger-tree
description: Inspect and improve documentation discovery using trigger-tree's local telemetry. Use for trigger-tree status, live dashboard, heat/cold maps, documentation health, router suggestions, setup, or diagnostics.
---
# 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.
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
Package observed Nov 5, 2026.
plugins_6a60bedd61688191aff576090846afeb
Download plugin data (JSON)