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/quangphu1912/codebase-analyzer/simulate-behaviornpx skills add quangphu1912/codebase-analyzer --skill simulate-behaviorgit clone --depth 1 https://github.com/quangphu1912/codebase-analyzerWhat 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 | $0.00032 | $0.01196 |
| Opus 5 | $0.00016 | $0.00598 |
| Sonnet 5 | $0.00006 | $0.00239 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
simulate-behavior 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Announce at start: "Using codebase-analyzer to simulate behavior."
Overview
Given a tool graph and gate map, predict behavior under different gate combinations. This is where analysis becomes prediction: you're not just mapping what exists, you're simulating what WOULD happen.
Prerequisites: Reads docs/analysis/tool-graph.md and docs/analysis/gate-map.md. Requires both Phase 3 prior skills complete.
Behavioral Fingerprinting
For each gate combination, produce a behavioral fingerprint:
- Available tools — which tools are active under this combination
- Active code paths — which execution branches are reachable
- Accessible data — what data stores, APIs, and resources are reachable
- Exposed capabilities — what the system can actually do in this state
Compare fingerprints to find surprising differences. Two configurations that look similar may have radically different behavioral profiles.
Temporal Analysis
How does behavior change over time?
- Feature flags that are on in dev but off in prod
- Capabilities scheduled for removal — deprecated tools still reachable
- Time-bombed code — trial features, expiration logic, rollout schedules
- Environment drift — config differences between dev/staging/production
State-Space Exploration
Enumerate gate combinations systematically. For N binary gates, there are 2^N possible states. Prioritize exploration:
| Priority | Category | Example | Why |
|---|---|---|---|
| 1 | Most likely states | Production config | This is what users actually experience |
| 2 | Most surprising states | Admin + external | Capability escalation risk |
| 3 | Most different from baseline | All gates open | Reveals full attack surface |
| 4 | Edge cases | Single gate flipped | Isolation failure detection |
Pruning: For large gate counts, group gates by domain (auth, features, providers) and explore intra-domain combinations exhaustively, inter-domain combinations at boundaries only.
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 · 131 lines · 32 tokens per session scan A a6b212fd573b
simulate-behavior is a skill published in the GitHub repository quangphu1912/codebase-analyzer (2 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,196 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
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…