A knowledge base for code repositories, stored as markdown files in a `.shadow/` folder that mirrors the source tree. It records discoveries such as bugs, edge cases, hidden agreements between parts of the code, and user preferences.

Use it to read project preferences, search discoveries, inspect cross-file findings, review experiment results, and check notes for specific files before making changes.

It helps coding agents check known project details before editing, debugging, or investigating code.

shadow-frog — Skill by microsoft

Install

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.

agentmods

npx agentmods add skills/microsoft/shadowfrog/shadow-frog

Any agent

npx skills add microsoft/ShadowFrog --skill shadow-frog

Clone the repo

git clone --depth 1 https://github.com/microsoft/ShadowFrog

Made for: Claude Code, Codex.

Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,408 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00117	$0.03408
Opus 5	$0.00059	$0.01704
Sonnet 5	$0.00023	$0.00682
Haiku 4.5	$0.00012	$0.00341

Measured 2d ago against content hash d50f78b029f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shadow-frog 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.

skills/shadow-frog/SKILL.md · 374 lines

How it starts

The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ShadowFrog

.shadow/ mirrors the source tree. Each source file has a .md shadow organized by symbol. Each symbol section contains discoveries — behavioral insights anchored to that code location.

Required Actions

Every time you work on code in a repo with .shadow/:

Read _prefs.md first — it contains project-wide conventions, user preferences, and things the user explicitly wants to avoid. Violating a preference wastes the user's time.
Read _cross/ discoveries — these are the highest-value findings, spanning multiple files. List _cross/ and read any files whose titles relate to the area you're working in. Cross-cutting discoveries reveal hidden contracts, interaction bugs, and design patterns that per-file shadows alone cannot capture.
Check _dreams/ for experiment results — _dreams/_index.md lists autonomous exploration experiments. Read reports relevant to your task — they contain verified bug analyses, attempted fixes, and architectural insights. Dreams may contain knowledge not yet distilled into per-file shadows, so always check when investigating a bug or unfamiliar area.
Before editing any file: read its shadow (.shadow/<path>.md), check _cross/ for cross-cutting discoveries about it, and apply what you learn. The shadow contains known bugs, edge cases, and implicit contracts discovered by previous sessions. Note: _index.md discovery counts may be stale — always check per-file shadows and _cross/ directly rather than relying solely on the index summary.
When the user explains something about code (gotcha, design intent, warning, history): write a source: user discovery to the shadow immediately. Do not ask where to put it — resolve the file::symbol anchor yourself by searching _index.md, shadow files, and session context (current file, recent edits).
When the user states a preference or convention (not tied to any specific file): write it to _prefs.md immediately.
After code changes: run /shadow-frog-update

Read the full file on GitHub · 374 lines

Changes

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 · 374 lines · 117 tokens per session scan A d50f78b029f9

Subscribe to this mod's changes

shadow-frog is a skill published in the GitHub repository microsoft/ShadowFrog (21 stars, last pushed 13d ago), licensed MIT. It adds 117 tokens to every session and 3,408 once invoked, about $0.0006 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 2026-08-30.

Code review Debugging Memory and context

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens