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/harnessgit 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 | $0.00719 |
| Opus 5 | $0.00008 | $0.00360 |
| Sonnet 5 | $0.00003 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
harness 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness
Launch the full Hierarchical Harness that combines the Karpathy AutoResearch loop with ClawTeam multi-agent parallelism.
How It Works
The harness has an Outer Loop (you, the Leader) and Inner Loops (spawned workers):
You (Leader):
score → identify bottleneck → delegate modules → merge gate → repeat
Workers (in isolated worktrees):
each runs: score → modify own module → score → report back
Execution
Step 1: Score and assess phase
Run bash score.sh and determine the current phase:
| Score | Phase | Action |
|---|---|---|
| < 0.05 | Foundation | YOU do it directly (single agent) |
| 0.05 ~ 0.30 | Core Algorithms | Spawn parallel workers: polar, qjl, uniform |
| 0.30 ~ 0.60 | Advanced | Spawn parallel workers: turbo, cache, simd-neon, bench |
| > 0.60 | Fine-tuning | YOU do it directly (precision matters) |
Step 2: For Foundation / Fine-tuning phases (single agent)
Use the /develop command pattern — implement one WBS item at a time.
Step 3: For parallel phases, spawn ClawTeam workers
$ARGUMENTS can override the target score (default: 0.9).
# Create team
clawteam team spawn-team tq-dev -d "quant.cpp development"
# Spawn workers for each independent module
clawteam spawn --team tq-dev --agent-name polar --workspace --repo . \
--task "Implement PolarQuant in src/core/tq_polar.c. Read refs/PolarQuant/models/modeling_llama_polar.py for algorithm. Write tests/test_polar.cpp. Run bash score.sh --quick after changes. Only modify: src/core/tq_polar.*, tests/test_polar.*"
clawteam spawn --team tq-dev --agent-name qjl --workspace --repo . \
--task "Implement QJL in src/core/tq_qjl.c. Read refs/QJL/models/llama2_utils_qjl.py for algorithm. Write tests/test_qjl.cpp. Run bash score.sh --quick after changes. Only modify: src/core/tq_qjl.*, tests/test_qjl.*"
Step 4: Wait and merge gate
# Wait for all workers
clawteam task wait tq-dev --timeout 1800
# Merge gate: merge each worker one-by-one
# For each worker branch:
# 1. git merge <branch> --no-edit
# 2. bash score.sh --quick
# 3. If score dropped: git reset --hard HEAD~1
# 4. If score OK: continue
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 · 79 lines · 15 tokens per session scan A 11099eda2c91
harness 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 719 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).