agentmods.dev

letter-hooker

letter-hooker is a skill for Codex from ellmos-ai/skills. It costs 129 tokens per session (1,304 once invoked), scanned B, original, MIT.

A prompt-level startup and rule-loading layer for AI agents that lack built-in lifecycle hooks. It checks project instruction files and adds required context before work begins.

In plain words
What is it for?
Use it to load instructions from files such as AGENTS.md or README.md, run memory and maintenance checks, and add governance guidance to agent prompts.
Why use it?
It reduces the risk that an agent misses important project rules or skips required checks before complex or destructive changes.

Skill for Codex

Written for Codex: reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python OneDrive/.SYNC/scripts/agy_kontext_and_workflow_loader.py.

not rated 4repo today B scan 129 tokens original MIT

Good fit Use it to load instructions from files such as AGENTS.md or README.md, run memory and maintenance checks, and add governance guidance to agent prompts.

Compare 6 skills from other repositories ↓
View source ↗ ellmos-ai/skills
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/ellmos-ai/skills
agentmods
npx agentmods add skills/ellmos-ai/skills/letter-hooker

Made for: Codex.

Wrote 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.

agentmods badge for letter-hooker

README.md
[![agentmods](https://agentmods.dev/badge/skills/ellmos-ai/skills/letter-hooker/github.svg)](https://agentmods.dev/skills/ellmos-ai/skills/letter-hooker)
Your own site
<a href="https://agentmods.dev/skills/ellmos-ai/skills/letter-hooker"><img src="https://agentmods.dev/badge/skills/ellmos-ai/skills/letter-hooker/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.

agentmods 80×15 button for letter-hooker

Your own site · 80×15
<a href="https://agentmods.dev/skills/ellmos-ai/skills/letter-hooker"><img src="https://agentmods.dev/badge/skills/ellmos-ai/skills/letter-hooker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,304 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00129 $0.01304
Opus 5 $0.00064 $0.00652
Sonnet 5 $0.00026 $0.00261
Haiku 4.5 $0.00013 $0.00130

Measured 6d ago against content hash cb03d9a06cc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

letter-hooker scanned grade B with 1 finding 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 6d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Der **Letter-Hooker**-Skill erweitert `automation-self-care` für KI-Agenten-Frameworks (wie **Antigravity / Gemini CLI**), die keine nativen, ereignisgetriebenen JSON-Lifecycle-Hook-Loader besitzen (z. B. `~/.claude/sett
skills/infrastructure/letter-hooker/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Letter-Hooker (Prompt-Level Preflight & Governance Engine)

Der Letter-Hooker-Skill erweitert automation-self-care für KI-Agenten-Frameworks (wie Antigravity / Gemini CLI), die keine nativen, ereignisgetriebenen JSON-Lifecycle-Hook-Loader besitzen (z. B. ~/.claude/settings.json oder ~/.codex/hooks.json).

Statt sich auf passive Per-Keypress-Hooks zu verlassen, betreibt letter-hooker einen aktiven Prompt-Level-Preflight-Bootloader und Letter-Hook-Injection-Loop über geplante Tasks und Maintainer-Skripte (agy_kontext_and_workflow_loader.py).

Kernfähigkeiten

  1. Preflight-Bootloader & Dokument-Traversierungsregeln:

    • Aufwärts- & Abwärtssuche: Erzwingt strikte Anweisungen für Agenten, AGENTS.md, CLAUDE.md, START.md, RULES.md und README.md auf der aktuellen Arbeitsverzeichnis-Ebene zu prüfen. Fehlen sie, aufwärts traversieren, bis gefunden; dann abwärts prüfen.
    • Memory- & Gardener-Preflight: Pflicht-Preflight-Abfrage an gardener und memoryhooker, bevor destruktive oder komplexe Änderungen ausgeführt werden.

  2. Letter-Hooks-Katalog & Referenz-Links:

    • Modulare .md-Instruktionsdateien unter OneDrive/.SYNC/antigravity_kontext_and_workflow_loader_package/letter_hooks/.
    • Injiziert explizite file://-Links direkt in den sidecar.json-Prompt-Text, damit Agenten bei Aufruf exakte Sicherheits- und Workflow-Protokolle lesen.

  3. Tägliche Stichwortliste & selbstheilende Prompt-Anreicherung:

    • Pflegt eine tägliche STICHWORTLISTE.json aus aktiven/Standby-Tasks.
    • Analysiert Ausführungslogs (AUTOMATIONS-MEMORY.md) auf Fehlermuster (fehlender Kontext, fehlende Workflow-Anleitung, ungültige Pfade) und patcht Task-Prompts dynamisch.

  4. Skill- & Persona-Routing:

    • Prüft Task-Schlüsselwörter und mappt sie auf passende .SKILLS (z. B. infrastructure/condition, semantic-persona-routing, orchestrator, think, decide).

Read the full file on GitHub · 87 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 87 lines · 129 tokens per session scan B cb03d9a06cc5

Subscribe to this mod's changes

letter-hooker is a skill published in the GitHub repository ellmos-ai/skills (4 stars, last pushed today), licensed MIT. It adds 129 tokens to every session and 1,304 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Building agentsClaude CodeLLMMemory and contextai-skillsanthropicautomationbootloadergovernanceinfrastructureletter-hookerletter-hooksprompt-enrichmentself-care
Related

Other skills, from other repositories

llm-deployment

Use when lLM deployment and serving — vLLM, Ollama, TGI, llama.cpp. Model quantization, GPU optimization, API serving. Use when working with llm deployment.

oyi77/1ai-skills · 44 tokens

devops-expert

Expert-level DevOps practices, culture, automation, and continuous delivery. Use when the user mentions CI/CD, automation, infrastructure, or culture, or when the task involves DevOps Culture or Culture & Process.

personamanagmentlayer/pcl · 47 tokens

agent-self-improvement

Use when monitor performance of other skills, identify bottlenecks, suggest improvements, and auto-optimize the skill portfolio. Use when monitoring performance of other skills, identify bottlenecks, suggest improvements, and.

oyi77/1ai-skills · 47 tokens

kb

Use when querying and maintaining the knowledge base for project context, decisions, and architecture documentation on session start.

oyi77/1ai-skills · 23 tokens

find-skills

Use when automatically discover, evaluate, and activate community skills when local skills don't cover user needs. Includes credibility scoring and safety checks for complete OpenClaw self-sufficiency.

oyi77/1ai-skills · 39 tokens

joko-orchestrator

Use when deterministically coordinating autonomous planning and execution across available skills under strict guardrails.

oyi77/1ai-skills · 23 tokens