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 mitodl/agent-kit --skill extract-style-profilegit clone --depth 1 https://github.com/mitodl/agent-kitWrote 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/mitodl/agent-kit/extract-style-profile)<a href="https://agentmods.dev/skills/mitodl/agent-kit/extract-style-profile"><img src="https://agentmods.dev/badge/skills/mitodl/agent-kit/extract-style-profile/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/mitodl/agent-kit/extract-style-profile"><img src="https://agentmods.dev/badge/skills/mitodl/agent-kit/extract-style-profile.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 | $0.00167 | $0.02173 |
| Opus 5.5 | $0.00067 | $0.00869 |
| Sonnet 5.5 | $0.00033 | $0.00435 |
| Haiku 4.5 | $0.00017 | $0.00217 |
Grade C, and why
extract-style-profile scanned grade C with 1 finding 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 25d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
hand: `rm -rf repos/<name>/` with a trailing slash follows the symlink and deletes How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract a style profile
Turns years of git and GitHub history into rules an agent can follow, with the evidence attached. It works in three modes:
| Mode | Subject | Output |
|---|---|---|
person |
One human's GitHub login(s) and git identities | Their personal coding and communication style |
team |
Several members | Shared conventions with agreement levels, enforced vs emergent. No per-person grading |
repo |
One or more repositories, all human authors | The codebase's conventions |
The process is: collect data with the bundled scripts, cut it into per-era text corpora, run one evidence-bound analysis pass per dimension, spot-check, then synthesize a report. The scripts do the mechanical work; the analysis passes and the synthesis need judgment.
References (read when you reach the step that uses them):
- references/subject-schema.md:
subject.jsonfields, examples per mode, choosing eras and the AI cutoff - references/analysis-brief.md: the brief every analysis pass reads
- references/dimensions.md: the checklist for each analysis pass
- references/pitfalls.md: data artifacts that look like style but aren't
- references/report-template.md: report structure and synthesis rules
Before starting
Consent and scope. Profiling a person means reading everything they wrote in
public and private repos the token can see. Run person mode on yourself, or on
someone who asked for it. For team mode, confirm the team knows, and keep the
output about conventions: no rankings, no per-person scorecards, no quotes that
single someone out.
Cost. A decade-long profile of one active engineer took ~25 minutes of data
collection and six parallel analysis passes of ~150-250k tokens each. A single repo
over two years is much smaller. Tell the user the rough size (from
activity/yearly.md) before launching the analysis passes, and offer to narrow
since, orgs, or the dimension list.
What ships with it
13 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.
- evals/evals.json 3.2 KB
- references/analysis-brief.md 5.4 KB
- references/dimensions.md 7.9 KB
- references/pitfalls.md 5.2 KB
- references/report-template.md 3.8 KB
- references/subject-schema.md 5.3 KB
- scripts/acquire_repos.py 4.7 KB runs code
- scripts/build_corpora.py 9.1 KB runs code
- scripts/common.py 6.1 KB runs code
- scripts/discover.py 5.1 KB runs code
- scripts/extract_commits.py 4.0 KB runs code
- scripts/fetch_github.py 19 KB runs code
- scripts/profile_stats.py 7.0 KB runs code
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.
- 25d ago First seen · 193 lines · 167 tokens per session scan C f6d768468b1f
extract-style-profile is a skill published in the GitHub repository mitodl/agent-kit (5 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 167 tokens to every session and 2,173 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.