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-updategit 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-update)<a href="https://agentmods.dev/skills/microsoft/shadowfrog/shadow-frog-update"><img src="https://agentmods.dev/badge/skills/microsoft/shadowfrog/shadow-frog-update/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-update"><img src="https://agentmods.dev/badge/skills/microsoft/shadowfrog/shadow-frog-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Data Exfiltration · line 54 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- medium Excessive Agency · line 111 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00074 | $0.01996 |
| Opus 5.5 | $0.00030 | $0.00798 |
| Sonnet 5.5 | $0.00015 | $0.00399 |
| Haiku 4.5 | $0.00007 | $0.00200 |
Grade A, and why
shadow-frog-update 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ShadowFrog Update
Updates .shadow/ from two sources: code changes (git diff) and conversational
knowledge (what the user said during the session). Prerequisite: .shadow/ exists.
Triggers
- Hook reminder:
preToolUseinjects a staleness warning when.shadow/_meta/state.json#last_commitdiffers from HEAD. The hook only reminds — it does NOT auto-run update. - Manual: user invokes
/shadow-frog-update
Phase 1: Detect Changes
# Read last_commit defensively: it may be missing, or the literal "none"
# when init ran without git (e.g. inside a container). `git diff none HEAD`
# would abort with "fatal: bad revision 'none'", and a missing key would
# make $LAST_COMMIT empty so `git diff HEAD` silently reports the wrong set.
LAST_COMMIT=$(python3 -c "import json,sys; print(json.load(sys.stdin).get('last_commit','none'))" < .shadow/_meta/state.json 2>/dev/null || echo "none")
if git rev-parse --verify "$LAST_COMMIT" >/dev/null 2>&1; then
git diff --name-only "$LAST_COMMIT" HEAD # committed changes since last update
else
echo "WARNING: state.json has no usable last_commit — falling back to a full re-scan."
fi
git diff --name-only HEAD # uncommitted changes
git diff --name-only --cached # staged changes
Categorize: modified, added, deleted, renamed.
Phase 2: Update Per-File Shadows (Symbol-Level)
For each changed file, update its shadow at the symbol level:
| Symbol change | Action |
|---|---|
| Added | Add the appropriate ##/### heading |
| Removed | Mark the section REMOVED; keep discoveries for history |
| Renamed | Move discoveries to the updated heading |
| Modified | Check whether discoveries still hold |
Only mark source: user discoveries stale if the symbol is completely removed.
Lightweight update (auto/hook): re-extract symbols, update headings, flag stale. Deep update (manual/dream): read diffs, generate new discoveries, verify existing ones.
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 · +4 lines 23f47fa975ad
- 1mo ago Changed · -6 lines c295c2dbbb45
- 1mo ago First seen · 202 lines · 74 tokens per session scan A fd447f0637da
shadow-frog-update is a skill published in the GitHub repository microsoft/ShadowFrog (30 stars, last pushed 6d ago), licensed MIT. It adds 74 tokens to every session and 1,996 once invoked, about $0.0003 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…