ShadowFrog is a suite of coding-agent skills that maintains a file-backed knowledge base of tacit information about a codebase, such as fragile dependencies, untested invariants, and hard-to-notice edge cases. It helps coding agents preserve lessons from code reading, experiments, and conversations across future work. The catalogue contains skills that create, update, explore, organize, and view this shadow knowledge base.
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 microsoft/ShadowFrog --skill shadow-frog-viewergit clone --depth 1 https://github.com/microsoft/ShadowFrogWrote 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/microsoft/shadowfrog/shadow-frog-viewer)<a href="https://agentmods.dev/skills/microsoft/shadowfrog/shadow-frog-viewer"><img src="https://agentmods.dev/badge/skills/microsoft/shadowfrog/shadow-frog-viewer/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/microsoft/shadowfrog/shadow-frog-viewer"><img src="https://agentmods.dev/badge/skills/microsoft/shadowfrog/shadow-frog-viewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 93 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00055 | $0.01658 |
| Opus 5.5 | $0.00022 | $0.00663 |
| Sonnet 5.5 | $0.00011 | $0.00332 |
| Haiku 4.5 | $0.00006 | $0.00166 |
Grade A, and why
shadow-frog-viewer 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 29d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ShadowFrog Viewer
User-facing inspection of .shadow/ content. Prerequisite: .shadow/ exists.
Agents navigate the Markdown files/symbols directly; this viewer is not a
required retrieval interface.
Primary: Python Helper Script
The companion script shadow-viewer.py lives in the same directory as
this SKILL.md file. To find and run it:
# Project install (Copilot CLI):
python3 .github/skills/shadow-frog-viewer/shadow-viewer.py [options]
# Or for Claude Code:
python3 .claude/skills/shadow-frog-viewer/shadow-viewer.py [options]
Available Views
| Command | What it shows |
|---|---|
--summary |
Overview: counts, source/status/label breakdown, per-file table, cross-cutting titles (default) |
--search QUERY |
Universal search — matches file names, symbol names, and discovery text. Includes cross-cutting and preferences |
--prefs |
Project-wide preferences |
--recent [N] |
N most recent discoveries with full content (default: 10) |
--labels LABEL |
Discoveries filtered by label (e.g., bug, security, bug,performance) |
--top FILE |
Top actionable discoveries for FILE — concise output (default: 3 entries, ~600 chars) suitable for the preToolUse hook. Includes both per-file shadow entries and any _cross/ discoveries that reference FILE. Verified discoveries rank first. |
--check-invariants |
Audit structural integrity — bidirectional cross-references, label/source/category enum compliance, heading format, no-orphan-back-pointer. Exits 0 if clean, 1 with one violation per line. Run after dream reconciliation or before commit. |
No arguments defaults to --summary.
Discovery views display the visible Markdown citation_score (missing means 0).
Search/label/top ordering uses it only after source trust and verification status;
refuted claims remain last. Reading, searching, and automatic previews do not
increment counts. The agent explicitly records deliberately consulted entries
with the core shadow-cite.py helper once per task. --recent is based on shadow
file modification time, which includes citation updates, not discovery creation time.
What ships with it
2 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.
- 29d ago Changed · +9 lines · +2 tokens per session d659d2dded93
- 1mo ago Changed · +9 lines 61a919042392
- 1mo ago Changed · -32 lines 4e7a7a92d839
- 1mo ago First seen · 163 lines · 53 tokens per session scan A 8e55d7d85a43
shadow-frog-viewer is a skill published in the GitHub repository microsoft/ShadowFrog (30 stars, last pushed 6d ago), licensed MIT. It adds 55 tokens to every session and 1,658 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…