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/quantumaikr/quant.cpp/developgit clone --depth 1 https://github.com/quantumaikr/quant.cppWhat 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 | $0.00015 | $0.00399 |
| Opus 5 | $0.00008 | $0.00199 |
| Sonnet 5 | $0.00003 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
develop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Develop
Autonomous single-agent development loop following the Karpathy AutoResearch pattern.
Protocol
You are an autonomous development agent for quant.cpp. Follow this loop exactly:
Step 1: Assess
- Run
bash score.sh --quickto see current score - Read
docs/wbs_v0.1.mdto find the next unchecked- [ ]item
If the user specified a module ($ARGUMENTS), focus only on WBS items related to that module.
Step 2: Implement
- Read
program.mdandCLAUDE.mdfor specifications - Read the relevant reference code in
refs/before implementing - Implement the WBS item (create/edit files)
- Follow module ownership rules from CLAUDE.md — only modify files you own
Step 3: Verify
- Run
bash score.sh --quick - If score improved or stayed the same: proceed
- If score dropped: revert your changes and try a different approach
- Ensure all tests pass:
cd build && ctest --output-on-failure
Step 4: Commit
- Mark the WBS item as
[x]indocs/wbs_v0.1.md - Stage only the files you changed (not refs/, not .score_history)
- Commit with a descriptive message
Step 5: Report
- Show the user: what was implemented, score before → after, next item
Rules
- ONE WBS item per invocation. Small, correct, incremental.
- Never modify files in
refs/,program.md, orscore.sh - Always read reference code before implementing algorithms
- If build fails, fix the build before doing anything else
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 · 46 lines · 15 tokens per session scan A 6f30294a1fe8
develop is a command published in the GitHub repository quantumaikr/quant.cpp (399 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 399 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 2026-09-01.
Other commands, from other repositories
amk-autoresearch
Launch the unattended / overnight AMK autoresearch driver on $ARGUMENTS (model [gpu] [minutes|iters]).
amk-optimize
Drive an interactive AMK propose -> eval -> keep/revert megakernel schedule session on $ARGUMENTS (model [gpu]).
amk-compile
One-shot compile + verify a model into a CUDA megakernel via amk compile on $ARGUMENTS (model [gpu]).
ARCHITECTURE
Command "ARCHITECTURE" from cloudrift-ai/emmy, covering commands architecture, layered design, layers, emmy/recipe/ — recipe library and emmy/deploy/ — deploy library.
EXPECT
Expect command describes the desired output of the task (after post-processing).
FORMAT
Format command describes the desired output of the task (after post-processing).