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 skills add yogsoth-ai/de-anthropocentric-research-engine --skill optimization-loopgit clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engineWrote 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/skills/yogsoth-ai/de-anthropocentric-research-engine/optimization-loop)<a href="https://agentmods.dev/skills/yogsoth-ai/de-anthropocentric-research-engine/optimization-loop"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/de-anthropocentric-research-engine/optimization-loop/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/skills/yogsoth-ai/de-anthropocentric-research-engine/optimization-loop"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/de-anthropocentric-research-engine/optimization-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.02350 |
| Opus 5.5 | $0.00026 | $0.00940 |
| Sonnet 5.5 | $0.00013 | $0.00470 |
| Haiku 4.5 | $0.00006 | $0.00235 |
Grade A, and why
optimization-loop 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 29d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
optimization-loop
You are the optimizer. You run a pseudo-NN training loop that produces labeled research-design samples. You are the ONLY continuously-running CC; the user-simulator and research-executor are spawned fresh each run. Disk is the only source of truth — your memory is not.
§loop — the two-level nested batch loop
LOOP-2 (epochs/batches, runs to convergence) wraps LOOP-1 (one batch = 48 runs = 8 topics × 6 rungs).
Epoch start (once):
python ../../scripts/new_run_id.py --runs-root runs→ capturerun_id. Emit tracerun_start.
Batch start (each batch):
2. batch_id = the highest batch-N in runs/<run_id>/weights/ (cold start =
batch-0; do NOT pre-increment). Emit batch_start.
3. Generate configs from the current weights: call
../../generator/gen_configs.py main(out_dir, w) (it is main(out_dir, w),
NOT an argparse CLI — invoke via a one-line python -c that imports it and
passes the loaded weights/<batch_id>.json). M1 note: gen_configs names
configs config_{rung}.json (rung only) — at 48 configs across 8 topics this
collides; a STAGE-2 patch must give them topic-bearing names before this loop
runs for real at STAGE 5.
Per run (8 topics × 6 rungs = 48):
4. Spawn the user-simulator CC (see §tools). Inject its research_config.
5. The simulator spawns the research-executor CC, injects the topic + bias + the
2 mandatory rules (the executor MUST load formated-specs then
formated-results).
6. Simulator ↔ executor talk for the card's turn budget. Emit dialogue_turn
per exchange.
7. python ../../scripts/save_transcript.py --logs-dir <REQUIRED> --cwd <exec-cwd> --sample <sample> --out runs/<run_id>/transcripts/<sample>.md. --logs-dir
is REQUIRED, no default (privacy red line).
8. python ../../scripts/concat_triple.py --run-dir runs/<run_id> --sample <sample>.
9. python scripts/run_codex_loss.py loss1 --transcript … --config … --skill-md ../injection-fidelity/SKILL.md --out runs/<run_id>/loss/<sample>.loss1.json.
Emit rung_done.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 29d ago Changed · +2 lines 21fb0457d44b
- 1mo ago First seen · 167 lines · 65 tokens per session scan A a5f39bd077dc
optimization-loop is a skill published in the GitHub repository yogsoth-ai/de-anthropocentric-research-engine (503 stars, last pushed 17d ago), licensed Apache-2.0. It adds 65 tokens to every session and 2,350 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…