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 skills add escapeboy/ai-prompts --skill code-researchgit clone --depth 1 https://github.com/escapeboy/ai-promptsWrote 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/escapeboy/ai-prompts/code-research)<a href="https://agentmods.dev/skills/escapeboy/ai-prompts/code-research"><img src="https://agentmods.dev/badge/skills/escapeboy/ai-prompts/code-research/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/escapeboy/ai-prompts/code-research"><img src="https://agentmods.dev/badge/skills/escapeboy/ai-prompts/code-research.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00095 | $0.01714 |
| Opus 5.5 | $0.00038 | $0.00686 |
| Sonnet 5.5 | $0.00019 | $0.00343 |
| Haiku 4.5 | $0.00010 | $0.00171 |
Grade A, and why
code-research 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 8d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Research
Systematic, grounded research of a codebase by fanning out parallel background agents over non-overlapping slices, verifying their findings, and synthesizing a durable knowledge base. Works identically on a local project or a cloned git repo. This is the method behind a multi-agent "understand + audit + gap-analyze this codebase" run.
When to use (and when NOT)
| Use this skill | Use something simpler instead |
|---|---|
| "Analyze / audit this whole codebase" | One symbol/file lookup → codebase-memory-mcp search_graph / Grep directly |
| "What's built / missing / unfinished / security / UI-UX" | "How does function X work" → 2-3 get_code_snippet + trace_path calls |
| "Review every line / 100% coverage" | A quick question answerable from one file → just Read it |
| Research an unfamiliar repo (local or git URL) | A change you're about to make in a known area → make it |
| Competitor / feature-gap analysis across two codebases | A diff review of pending changes → /code-review |
| Produce implementation plans grounded in an existing codebase | Spawning agents that must talk to each other mid-task → agent-team |
If the answer fits in a few tool calls, do NOT spin up agents — this skill is for breadth that overflows one context.
Core principles (non-negotiable)
- Grounded, don't assume. Every claim cites
path:lineand is verified against real code. Feature presence may be inferred from concrete files/routes/models, but never invented. Tell agents this verbatim. - Parallel + non-overlapping. Each agent owns a disjoint slice (domain, directory, or integration) so there are no shared-file write conflicts. Agents run in the background; you acknowledge completions and wait.
- Agents write their own notes. Each agent writes to its OWN knowledge-base path (distinct filename) and returns a short summary — never a shared file. This is what makes parallel writes safe.
- Progressive-disclosure KB. A thin top index → sub-indexes → detail notes. Everything reachable from one entry point. Cross-link with
[[wikilinks]]. - Verify, then correct. A second independent pass re-checks claims at cited lines and hunts missed logic. When it finds an error, fix the note — do not leave both versions.
What ships with it
6 files 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.
- 8d ago First seen · 85 lines · 95 tokens per session scan A 2a46b8576e98
code-research is a skill published in the GitHub repository escapeboy/ai-prompts (91 stars, last pushed 9d ago), licensed MIT. It adds 95 tokens to every session and 1,714 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-08.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…