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/gru-953/mta_plugin/recallgit clone --depth 1 https://github.com/GRU-953/MTA_PluginWhat 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 | $0.00017 | $0.00194 |
| Opus 5 | $0.00009 | $0.00097 |
| Sonnet 5 | $0.00003 | $0.00039 |
| Haiku 4.5 | $0.00002 | $0.00019 |
Grade A, and why
recall 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 today.
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
Answer the user's question from local memory using the recall tool.
Question: $ARGUMENTS
Steps:
- Call
recallwith the question (andprojectif the user named one). - It runs a local, model-free BM25 keyword search and returns a small relevant slice — theme summaries and entity cards with their source documents. It never returns whole documents.
- Answer the user's question grounded in those hits, citing the source document names
where provided. If
statusisno_memory, suggest running/memorisefirst. - If the result has
low_confidence: true(or no hits clear the relevance floor), tell the user the memory doesn't contain a confident answer rather than guessing.
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.
- today First seen · 19 lines · 17 tokens per session scan A cc194be8f1c7
recall is a command published in the GitHub repository GRU-953/MTA_Plugin (1 stars, last pushed 26d ago), licensed MIT. It adds 17 tokens to every session and 194 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 2026-08-31.
Other commands, from other repositories
svg-diagram
Create or update polished SVG architecture diagrams with automatic quality verification.
example-command
An example slash command that demonstrates command frontmatter options (legacy format).
default-cmd
In the default commands dir, which the declared path replaces.
enrich
Enrich project memory by mining 100 recently merged PRs: extracts decisions, conventions, gotchas, and architectural facts from PR discussions, review comments, and PR bodies.
reportloop
Interactively walk through all issues in REVIEWREPORT.md: explains each issue, asks to fix or skip, handles follow-up questions, and applies fixes one by one in severity order.
reviewcrew
Run a full codebase audit: spawns all specialist reviewers in parallel and writes a consolidated report to REVIEWREPORT.md.