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 | $0.00053 | $0.02381 |
| Opus 5 | $0.00026 | $0.01190 |
| Sonnet 5 | $0.00011 | $0.00476 |
| Haiku 4.5 | $0.00005 | $0.00238 |
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 12d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ingesting a repo into Metatron with an LLM (OKF candidates)
Overview
Metatron captures a codebase's real implementation decisions — preferred patterns,
rejected approaches, edge cases, internal conventions — as structured records.
Agents consume them either over MCP, or — in files-first mode — by reading these
OKF files in git directly, in which case the files are the source of truth and the
database is just a rebuildable serving index. The built-in metatron ingest <path>
uses an Anthropic model to extract those records. This skill lets any LLM/agent
do the extraction instead, by writing the same records as plain
Open Knowledge Format (OKF) v0.1
markdown files. metatron mirror import then reads those files into the store — no
API key, no ingest run. The git-tracked bundle is Metatron's implementation of the
Repository Context Layer — see the
context-md manifesto
for the rationale behind git-native, agent-maintained project context.
The one invariant you must respect: an LLM never decides what is canonical.
Crossing the canonical boundary is always human-gated: a human moving a file into
decisions/ — or approving the pull request that puts it there — is the curation
act. By default, write to context/candidate/ only; the single sanctioned
exception is the human-directed, PR-gated flow described in "Where to write"
below. Never choose decisions/ on your own initiative.
Directory name:
context/is the default knowledge-base directory. A repo may configure another name (context_dirinmetatron.toml,METATRON_CONTEXT_DIR, or--context-diron the mirror commands); pre-rename repos may still usemetatron/. The layout inside is identical — substitute the configured name.
When to use
- You want to bootstrap a repo's decisions but can't/won't run
metatron ingest(no Anthropic key, a different model, an offline agent, a CI step). - You're hand-authoring or LLM-authoring conventions to feed Metatron as files.
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.
- 12d 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 (24 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 2,381 once invoked, about $0.0003 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.
Other skills, from other repositories
state-management
STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.
mem0-integration
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
context-preservation
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
persistent-memory
Observation capture and retrieval across sessions. Stores decisions, discoveries, and bugfix patterns. Searchable via tags and relevance scoring.
context-management
Project context loading, isolation, and persistent state management across CCPM sessions.
importing-a-codebase
Use when the repo holds real source code but no specs: the existing-codebase branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for empty workspaces (starting-a-new-project) or feature work in a specced project (brainstorming).