Borrowing it
Nothing to install: this file belongs to JanoshMoshiri/MarkdownLLM. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JanoshMoshiri/MarkdownLLM/main/.claude/commands/orient.mdgit clone --depth 1 https://github.com/JanoshMoshiri/MarkdownLLMWrote 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/commands/janoshmoshiri/markdownllm/orient)<a href="https://agentmods.dev/commands/janoshmoshiri/markdownllm/orient"><img src="https://agentmods.dev/badge/commands/janoshmoshiri/markdownllm/orient/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/commands/janoshmoshiri/markdownllm/orient"><img src="https://agentmods.dev/badge/commands/janoshmoshiri/markdownllm/orient.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 | $0.00029 | $0.00955 |
| Opus 5.5 | $0.00012 | $0.00382 |
| Sonnet 5.5 | $0.00006 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
orient scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 20d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Why this is a command. The startup hook's channel is capped at 10,000
characters and the session-start emission is near three times that, so the
hook delivers the digest and defers the kernel — and a read the entry
file merely instructs is economised
(emitted-content-is-read-instructed-content-is-economised). The two blocks
below ran before you saw this prompt and their output replaced the commands:
content, not instruction. Read both end to end; then walk.
The operative kernel (emitted)
!sh -c 'f=$(sed -n "s/^framework_root: *//p" AGENTS.md 2>/dev/null | head -1 | tr -d "\042\047 \r"); d=; for c in "$f" "$PWD/$f"; do [ -n "$f" ] && [ -f "$c/.markdownllm" ] && { d=$c; break; }; done; if [ -z "$d" ]; then d=$PWD; while [ "$d" != / ] && [ ! -f "$d/.markdownllm" ]; do d=${d%/*}; [ -n "$d" ] || d=/; done; fi; if [ -f "$d/tools/mdllm.sh" ]; then sh "$d/tools/mdllm.sh" session-start . --kernel 2>&1; else echo "mdllm: no framework root found from $PWD — no .markdownllm above it and no usable framework_root in AGENTS.md; run session-start by hand through the launch route in AGENTS.md"; fi; exit 0'
The session-start digest (emitted)
!sh -c 'f=$(sed -n "s/^framework_root: *//p" AGENTS.md 2>/dev/null | head -1 | tr -d "\042\047 \r"); d=; for c in "$f" "$PWD/$f"; do [ -n "$f" ] && [ -f "$c/.markdownllm" ] && { d=$c; break; }; done; if [ -z "$d" ]; then d=$PWD; while [ "$d" != / ] && [ ! -f "$d/.markdownllm" ]; do d=${d%/*}; [ -n "$d" ] || d=/; done; fi; if [ -f "$d/tools/mdllm.sh" ]; then sh "$d/tools/mdllm.sh" session-start . --digest 2>&1; else echo "mdllm: no framework root found from $PWD — no .markdownllm above it and no usable framework_root in AGENTS.md; run session-start by hand through the launch route in AGENTS.md"; fi; exit 0'
The walk — the judgement half, yours, now
Receipt first: does the kernel block end with its [kernel emitted whole — …]
trailer, and does the digest carry no [truncated] marker? If either fails,
say so and read the named file in full before continuing — a block that did
not land whole is not loaded.
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.
- 20d ago First seen · 47 lines · 29 tokens per session scan A 315d5749653c
orient is a command published in the GitHub repository JanoshMoshiri/MarkdownLLM (5 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 955 once invoked, about $0.0001 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 2026-10-18.
orient compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| orientJanoshMoshiri/MarkdownLLM | Command | 5 | 4d ago | MIT | A | 29 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |