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 agentmods add commands/ojspace/md-anything/ingestgit clone --depth 1 https://github.com/ojspace/md-anythingWhat 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 | $0.00011 | $0.00345 |
| Opus 5 | $0.00005 | $0.00172 |
| Sonnet 5 | $0.00002 | $0.00069 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
ingest scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Batch-convert all supported files in a folder using the mda CLI.
Usage: /md-anything:ingest <folder> [options]
Examples:
/md-anything:ingest ./notes/md-anything:ingest ./vault -r— recursive/md-anything:ingest ./notes -o ./output -r— write files to output dir
Steps
-
Run ingest with JSON output:
mda ingest "$ARGUMENTS" --json -
Parse the JSON response:
converted— number of files successfully convertedskipped— files that were skipped (unsupported or unreadable)failed— files that faileddocs— array of{ fileName, title, sourceType, source, metadata }
-
Report a summary to the user: how many converted, skipped, failed.
-
If any files failed, explain that ingest only returns counts plus converted docs, and suggest
mda doctorwhen missing local tools may be the cause.
Useful flags to pass through from the user's request
-ror--recursive— process subdirectories-o <dir>— write.mdfiles to an output directory
Notes
- If
mdais not installed, instruct the user to run:bun install -g md-anything - Current ingest walks supported files in the folder; it does not process source manifests or generate graph/index artifacts
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.
- 2d ago First seen · 40 lines · 11 tokens per session scan A fd4ba0ad8bab
ingest is a command published in the GitHub repository ojspace/md-anything (49 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 345 once invoked, about $0.0001 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 commands, from other repositories
crux-meditate
Recursive memory-informed exploration of themes, topics, and intent through 3-level deep agent inception.
crux-compress
Compress markdown rule files, code files, and images into CRUX notation for token/size efficiency.
crux-test
Run comprehensive tests on all CRUX features via LLM interaction and produce a markdown test report.
crux-dream
Post-execution memory extraction and REM sleep rebalancing.
crux-recall
Decompress, query, and display CRUX memories in human-readable form.
crux-forget
Remove memories from the CRUX memory corpus.