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 skills/miaoy0ushan/fp/optimize-pathnpx skills add MiaoY0uShan/FP --skill optimize-pathgit clone --depth 1 https://github.com/MiaoY0uShan/FPWrote 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/miaoy0ushan/fp/optimize-path)<a href="https://agentmods.dev/skills/miaoy0ushan/fp/optimize-path"><img src="https://agentmods.dev/badge/skills/miaoy0ushan/fp/optimize-path.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00030 | $0.02382 |
| Opus 5 | $0.00015 | $0.01191 |
| Sonnet 5 | $0.00006 | $0.00476 |
| Haiku 4.5 | $0.00003 | $0.00238 |
Grade A, and why
fp-optimize-path 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 3d 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 — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FP: Optimize Path
Choose the smallest stable path that reaches the stated goal with verified progress.
Then compile the selected route into the final Execution Brief.
This skill does not write code. It does not expand the MVP. It converts upstream FP reports into a short execution contract that a coding agent can follow.
Primary output
The primary output of this skill is not a long plan.
The primary output is a compiled Execution Brief:
question-requirements output
+ delete-scope output
+ semantic-architecture output
+ optimize-path selected route
+ shorten-iteration TDD loops, if needed
= compiled Execution Brief
The brief is the contract for execution.
Contract compiler requirement
optimize-path must compile upstream FP outputs into the final Compiled Execution Brief.
The final brief must include:
- Context Budget Contract;
- Context Diet Map;
- files to read, touch, and avoid;
- selected path;
- TDD micro-loops, when needed;
- Failure-to-Smaller-Task Protocol;
- Evidence Ledger handoff;
- Metrics to record.
If the required context limits or scope boundary are missing, create them before execution begins.
Use when
Use this skill when:
question-requirementshas identified the real goal.delete-scopehas defined the MVP nucleus and scope boundary.semantic-architecturehas defined module boundaries for larger tasks, if needed.- The agent is ready to choose a bounded coding path.
- The final deliverable should be an Execution Brief.
Do not use this skill to redesign the product goal or expand the MVP.
Core principle
Choose the smallest stable path that reaches the stated goal with verified progress.
A good path is:
- one that lands on the stated goal, not a nearby outcome
- small enough to execute safely
- stable enough to avoid avoidable failure
- easy to verify
- reversible where possible
- free of unnecessary scope
- clear enough to compile into a brief
Path filters
Use the reuse ladder, then these four filters before choosing an implementation path.
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.
- 3d ago First seen · 451 lines · 30 tokens per session scan A 4b69af55097c
fp-optimize-path is a skill published in the GitHub repository MiaoY0uShan/FP (3 stars, last pushed 27d ago), licensed MIT. It adds 30 tokens to every session and 2,382 once invoked, about $0.0002 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 skills, from other repositories
digital-health-clinical-asr-finetune
Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).
doca-compress
Use this skill for hands-on DOCA Compress programming on a BlueField DPU, ConnectX NIC, or host with DOCA — enabling compress-deflate, decompress-deflate, decompress-lz4-stream, or decompress-lz4-block tasks on a docacompress context (the hardware supports DEFLATE both directions plus LZ4 decompress; LZ4 encode is NOT…
doca-dms
Operate NVIDIA DOCA Management Service (dmsd + dmspe) on a BlueField, Arm/x86 host, or Kubernetes pod: choose deployment and authentication, configure -allowedusers and dmsgroup, use gNMI Get/Set/Subscribe, run supported gNOI workflows, and debug frontend/backend failures. Trigger even without "DMS" for "manage a…
git-ai-search
Search and restore AI conversation context from git history.
hyperpod-version-checker
Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches…
helmor-debug-operate
Operate, reproduce, and debug a running local Helmor desktop development build through the Tauri MCP bridge. Use when the user asks to use Tauri MCP, towery MCP, the local dev build, the Tauri webview, visual end-to-end validation, UI automation, screenshots, DOM/accessibility snapshots, IPC or log tracing…