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/analyze-prompt-influencenpx skills add quangphu1912/codebase-analyzer --skill analyze-prompt-influencegit clone --depth 1 https://github.com/quangphu1912/codebase-analyzerWrote 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/quangphu1912/codebase-analyzer/analyze-prompt-influence)<a href="https://agentmods.dev/skills/quangphu1912/codebase-analyzer/analyze-prompt-influence"><img src="https://agentmods.dev/badge/skills/quangphu1912/codebase-analyzer/analyze-prompt-influence.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 5.1 | $0.00038 | $0.01207 |
| Opus 5 | $0.00019 | $0.00603 |
| Sonnet 5 | $0.00008 | $0.00241 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
analyze-prompt-influence 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 6d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Announce at start: "Using codebase-analyzer to analyze prompt influence."
Overview
Compare two influence sources: (1) what the system prompt instructs, (2) what the code actually enforces. Determine the gap between "told to do" and "forced to do."
Prerequisite: Reads docs/analysis/tool-graph.md and docs/analysis/gate-map.md (from extract-tool-graph and map-feature-gates).
The Brilliant Secret
Prompt is not behavior. This is the single most important insight for analyzing control architecture. A system prompt that says "don't do X" is a suggestion. Code that removes tool X from the tool registry is enforcement. The gap between them is where the real control architecture lives -- and where the real vulnerabilities hide.
Every "prompt-driven" behavior falls somewhere on this spectrum:
Suggestion <-------> Enforcement
| |
v v
Prompt only Code only
"Be concise" Token limit=500
"Don't do X" Tool X not registered
"Focus on Y" SQL filter WHERE y=Y
Most systems have behaviors scattered across the entire spectrum. The analyst's job is to map each one and find the gaps.
Part 1: Prompt Control Extraction
- Find all system prompt templates and instructions
- Map prompt-driven behaviors: what the prompt tells the system to do
- Identify prompt variables and conditional sections
- Find prompt versioning/A-B testing patterns
- For each prompt instruction, classify its enforcement level:
- Suggestion only: Prompt says it, no code backing (e.g., "be helpful")
- Partially enforced: Prompt + some code checks (e.g., "don't access files" + partial path filtering)
- Fully enforced: Code makes prompt instruction redundant (e.g., "don't use shell" + shell tool removed from registry)
Part 2: Gap Analysis Methodology
For each behavior dimension, run this three-question protocol:
- What does the prompt SAY to do? (declared control)
- What does the code ENFORCE? (actual control)
- What's the gap? (The gap IS the control architecture. A wide gap means the system relies on the model's compliance, not engineering controls.)
What ships with it
1 file 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.
- 6d ago First seen · 100 lines · 38 tokens per session scan A 9a960fc712b2
analyze-prompt-influence is a skill published in the GitHub repository quangphu1912/codebase-analyzer (2 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 1,207 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
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…