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 skills add kerbelp/metatron --skill context-okf-llm-ingestgit clone --depth 1 https://github.com/kerbelp/metatronWrote 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/skills/kerbelp/metatron/context-okf-llm-ingest)<a href="https://agentmods.dev/skills/kerbelp/metatron/context-okf-llm-ingest"><img src="https://agentmods.dev/badge/skills/kerbelp/metatron/context-okf-llm-ingest/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.
<a href="https://agentmods.dev/skills/kerbelp/metatron/context-okf-llm-ingest"><img src="https://agentmods.dev/badge/skills/kerbelp/metatron/context-okf-llm-ingest.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00045 | $0.01566 |
| Opus 5.5 | $0.00018 | $0.00626 |
| Sonnet 5.5 | $0.00009 | $0.00313 |
| Haiku 4.5 | $0.00005 | $0.00157 |
Grade A, and why
context-okf-llm-ingest 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 27d 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring repository decisions with an LLM
Overview
Capture a codebase's real implementation decisions — preferred patterns, rejected
approaches, edge cases, internal conventions — as structured OKF markdown files.
Any coding agent can author them; metatron ingest is not required.
In files-first mode, agents read the Git-tracked files directly. No database, MCP server, or import is needed. The files are a portable Open Knowledge Format (OKF) v0.1 bundle and implement the Repository Context Layer.
Human review is the canonical boundary. Follow the repository's configured review gate: either a human-reviewed PR containing decision files, or separate review of staged candidates. Authoring on a branch is not permission to merge.
Directory name:
context/is the default knowledge-base directory. Honor the configuredcontext_dirinmetatron.tomlorMETATRON_CONTEXT_DIR; pre-rename repos may still usemetatron/. Substitute the resolved directory in all paths and commands below. In monorepos use the knowledge base nearest the code, such asapps/web/context/, and the workspace's installed skills.
Workflow (files-first)
- Read the repository instructions,
context.md, and relevant existing decisions before exploring implementation details. Check the review gate below. - Inspect source and tests. Extract prescriptive, non-obvious conventions supported by that evidence, rather than generic framework advice.
- Write one OKF file per new convention in the gate's destination directory. Amend an existing decision when it already covers the same convention.
- Validate the destination with
metatron files lint --path context/decisionsfor the PR gate, ormetatron files lint --path context/candidatefor staging. - Inspect
git status --shortand the complete diff. New untracked files need their own view, e.g.git diff --no-index -- /dev/null context/decisions/repo-pattern-for-stores.md(exit 1 means differences). Include the decision changes in the human-reviewed PR, or present the staged candidates for human selection. Stop before merging or promoting anything without the required human review.
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.
- 27d ago Changed · -58 lines · -8 tokens per session a565e5763920
- 1mo ago First seen · 194 lines · 53 tokens per session scan A 80d9058adee5
context-okf-llm-ingest is a skill published in the GitHub repository kerbelp/metatron (27 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 1,566 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
agent-v3-memory-specialist
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.
agent-memory-coordinator
Agent skill for memory-coordinator - invoke with $agent-memory-coordinator.
agent-swarm-memory-manager
Agent skill for swarm-memory-manager - invoke with $agent-swarm-memory-manager.
agent-collective-intelligence-coordinator
Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator.
memory-management
AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: need to store successful patterns, searching for similar solutions, semantic lookup of past work, learning from previous…
importing-a-codebase
Use when asked to create the initial spec graph for an existing codebase that has source code but no specs. Normally reached via setting-up-a-project.