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/codebase-analysisnpx skills add MiaoY0uShan/FP --skill codebase-analysisgit clone --depth 1 https://github.com/MiaoY0uShan/FPWhat 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 | $0.00046 | $0.00533 |
| Opus 5 | $0.00023 | $0.00267 |
| Sonnet 5 | $0.00009 | $0.00107 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
fp-codebase 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 yesterday.
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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FP Codebase Analysis
Prefer code-review-graph MCP when available. Start with get_minimal_context_tool. Fall back to grep-based discovery when MCP is unavailable.
MCP Route
get_minimal_context_tool(~100 tokens) → community names and entry pointsdetect_changes_tool→ risk-scored functions, affected flows, test gapsget_impact_radius_tool→ blast radiusget_architecture_overview_tool→ hub/bridge nodessemantic_search_nodes_tool→ semantic queries
Load ../templates/code-review-graph-mcp-contract.md for the full 30-tool map.
Tree-sitter MCP Tier (fallback)
When code-review-graph MCP is unavailable but a tree-sitter code-search MCP is installed (e.g. nendotools/tree-sitter-mcp, cocoindex-code, claude-context), prefer it over grep for symbol lookup, call chains, and structural queries. Mark source: tree-sitter-mcp in the impact map. For repos over ~500k LOC or when structural queries return thousands of hits, prefer a hybrid vector-search MCP (claude-context, cocoindex-code) over tree-sitter alone.
Grep Fallback
git diff→ extract changed symbolsgrep -rnfor callers/importersGlobfor test files- Mark
source: grep-fallbackin impact map
Load ../templates/codebase-impact-map.md for the output template.
Post-Fix Triple Critique (on-demand, Medium+ only)
After a Medium or larger fix lands, optionally dispatch three parallel read-only review agents in independent domains — Reuse (ladder violations), Quality (defect patterns), Efficiency (waste) — then aggregate; the parent verifies critical findings itself. Never run this for Small routes or by default.
Standards vs Spec Paired Review (on-demand, PR scope only)
For PR-scope review, dispatch two parallel read-only reviewers with disjoint scopes: Standards (this repo's documented conventions, style, patterns) and Spec (the originating issue / PRD acceptance criteria). Report the two verdicts side by side — standards divergence is not spec divergence; do not average them. Never run for Small routes.
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.
- yesterday First seen · 40 lines · 46 tokens per session scan A b9e7b136ab74
fp-codebase is a skill published in the GitHub repository MiaoY0uShan/FP (3 stars, last pushed 25d ago), licensed MIT. It adds 46 tokens to every session and 533 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
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…
cupynumeric-migration-readiness
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment…