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/ecorkran/context-forge/analyzenpx skills add ecorkran/context-forge --skill analyzegit clone --depth 1 https://github.com/ecorkran/context-forgeWhat 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 | $0.00019 | $0.02104 |
| Opus 5 | $0.00010 | $0.01052 |
| Sonnet 5 | $0.00004 | $0.00421 |
| Haiku 4.5 | $0.00002 | $0.00210 |
Grade A, and why
analyze 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 2d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Analysis Workflow
This skill provides a complete analysis workflow for existing codebases. It is organized into stages that can be used independently or as a sequential pipeline.
Usage: Invoke /analyze and specify which stage to run, or start from Stage 1 for a full discovery workflow. Provide {project} and optionally {subproject} as context.
Stage 1: Analyze Codebase
Purpose: Perform discovery analysis of existing codebase to:
- Document system architecture and technology stack
- Identify technical debt and improvement opportunities
- Provide foundation for creating architectural components, slices, or maintenance tasks
- Create reference documentation for team members
This is reconnaissance work - not goal-oriented development.
Analyze the following existing codebase and document your findings. We want this to not only assist ourselves in updating and maintaining the codebase, but also to assist humans who may be working on the project.
Expected Output
- Document your findings in
user/analysis/nnn-analysis.{topic}.mdwhere:- nnn starts at 940 (analysis range)
- {topic} describes the analysis focus (e.g., "initial-codebase", "dependency-audit", "architecture-review")
- Write in markdown format, following our rules for markdown output.
General Guidelines
- Document the codebase structure. Also note presence of any project-documents or similar folders which probably contain information for us.
- Document presence or average of tests, and an estimate of coverage if tests are present.
- Identify technologies and frameworks in use.
- What package managers are in use?
- Is there a DevOps pipeline indicated?
- Analysis should be concise and relevant - no pontificating.
- Add note in README as follows: Claude: please find code analysis details in {file mentioned above}.
Front End (if applicable)
- If this is a JS app, does it use React? Vue? Is it NextJS? Is it typescript, javascript, or both? Does it use TailWind? ShadCN? Something else?
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.
- 2d ago First seen · 199 lines · 19 tokens per session scan A ea74f12473a1
analyze is a skill published in the GitHub repository ecorkran/context-forge (5 stars, last pushed 21d ago), licensed MIT. It adds 19 tokens to every session and 2,104 once invoked, about $0.0001 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…